{"id":"https://openalex.org/W7125584057","doi":"https://doi.org/10.1145/3787104","title":"Bridging the Black Box: A Survey on Mechanistic Interpretability in AI","display_name":"Bridging the Black Box: A Survey on Mechanistic Interpretability in AI","publication_year":2026,"publication_date":"2026-01-23","ids":{"openalex":"https://openalex.org/W7125584057","doi":"https://doi.org/10.1145/3787104"},"language":"en","primary_location":{"id":"doi:10.1145/3787104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3787104","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098934039","display_name":"Shriyank Somvanshi","orcid":"https://orcid.org/0009-0008-3723-0607"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shriyank Somvanshi","raw_affiliation_strings":["Texas State University"],"raw_orcid":"https://orcid.org/0009-0008-3723-0607","affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744503","display_name":"Md Majharul Islam","orcid":"https://orcid.org/0009-0007-3670-6100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Monzurul Islam","raw_affiliation_strings":["Texas State University"],"raw_orcid":"https://orcid.org/0009-0007-3670-6100","affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058550807","display_name":"Amir Rafe","orcid":"https://orcid.org/0000-0002-4089-2088"},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Rafe","raw_affiliation_strings":["Utah State University"],"raw_orcid":"https://orcid.org/0000-0002-4089-2088","affiliations":[{"raw_affiliation_string":"Utah State University","institution_ids":["https://openalex.org/I121980950"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117281314","display_name":"Anannya Ghosh Tusti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anannya Ghosh Tusti","raw_affiliation_strings":["Texas State University"],"raw_orcid":"https://orcid.org/0009-0001-5102-5182","affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arka Chakraborty","orcid":"https://orcid.org/0000-0002-6315-2277"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arka Chakraborty","raw_affiliation_strings":["Texas State University"],"raw_orcid":"https://orcid.org/0000-0002-6315-2277","affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119062644","display_name":"Anika Baitullah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anika Baitullah","raw_affiliation_strings":["Texas State University"],"raw_orcid":"https://orcid.org/0009-0004-9714-0196","affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027098589","display_name":"Tausif Islam Chowdhury","orcid":"https://orcid.org/0009-0008-2385-8719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tausif Islam Chowdhury","raw_affiliation_strings":["Texas State University"],"raw_orcid":"https://orcid.org/0009-0008-2385-8719","affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086967940","display_name":"Nawaf Alnawmasi","orcid":"https://orcid.org/0000-0001-5753-3025"},"institutions":[{"id":"https://openalex.org/I4210088963","display_name":"University of Ha'il","ror":"https://ror.org/013w98a82","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210088963"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Nawaf Alnawmasi","raw_affiliation_strings":["University of Hail"],"raw_orcid":"https://orcid.org/0000-0001-5753-3025","affiliations":[{"raw_affiliation_string":"University of Hail","institution_ids":["https://openalex.org/I4210088963"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112503735","display_name":"Anandi Dutta","orcid":"https://orcid.org/0009-0002-7279-7752"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anandi Dutta","raw_affiliation_strings":["Texas State University"],"raw_orcid":"https://orcid.org/0009-0002-7279-7752","affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123746482","display_name":"Subasish Das","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subasish Das","raw_affiliation_strings":["Civil Engineering, Texas State University"],"raw_orcid":"https://orcid.org/0000-0002-1671-2753","affiliations":[{"raw_affiliation_string":"Civil Engineering, Texas State University","institution_ids":["https://openalex.org/I13511017"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5098934039"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":32.8796,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98683805,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"58","issue":"8","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9153000116348267,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9153000116348267,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.01510000042617321,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9747999906539917},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6054999828338623},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.42410001158714294},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.3456999957561493},{"id":"https://openalex.org/keywords/corporate-governance","display_name":"Corporate governance","score":0.3181000053882599}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9747999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512000203132629},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49410000443458557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47110000252723694},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C39389867","wikidata":"https://www.wikidata.org/wiki/Q380767","display_name":"Corporate governance","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C14224292","wikidata":"https://www.wikidata.org/wiki/Q13600188","display_name":"Conceptual framework","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3787104","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1982229380","https://openalex.org/W1996796871","https://openalex.org/W2084341220","https://openalex.org/W2118022153","https://openalex.org/W2149706766","https://openalex.org/W2282821441","https://openalex.org/W2585665652","https://openalex.org/W2792641098","https://openalex.org/W2793546384","https://openalex.org/W2945976633","https://openalex.org/W2962858109","https://openalex.org/W3010694149","https://openalex.org/W3109060525","https://openalex.org/W3132191748","https://openalex.org/W3134095442","https://openalex.org/W3138819813","https://openalex.org/W3197983285","https://openalex.org/W4213228517","https://openalex.org/W4224996539","https://openalex.org/W4229494842","https://openalex.org/W4297792514","https://openalex.org/W4312430207","https://openalex.org/W4323022345","https://openalex.org/W4390889563","https://openalex.org/W4393992045","https://openalex.org/W4400135851","https://openalex.org/W4400188660","https://openalex.org/W4404784049","https://openalex.org/W4410390425","https://openalex.org/W4412594747"],"related_works":[],"abstract_inverted_index":{"Mechanistic":[0],"interpretability":[1,75,115,164],"seeks":[2],"to":[3,131,155],"reverse-engineer":[4],"the":[5,58],"internal":[6],"logic":[7],"of":[8,57,108],"neural":[9],"networks":[10],"by":[11],"uncovering":[12],"human-understandable":[13],"circuits,":[14],"algorithms,":[15],"and":[16,37,48,64,84,94,102,137,148,169],"causal":[17,95,140],"structures":[18],"that":[19,27,104],"drive":[20],"model":[21],"behavior.":[22],"Unlike":[23],"post":[24],"hoc":[25],"explanations":[26],"describe":[28],"what":[29],"models":[30],"do,":[31],"this":[32,152],"paradigm":[33],"focuses":[34],"on":[35],"why":[36],"how":[38,113,162],"they":[39],"compute,":[40],"tracing":[41],"information":[42],"flow":[43],"through":[44],"neurons,":[45],"attention":[46],"heads,":[47],"activation":[49],"pathways.":[50],"This":[51],"survey":[52,153],"provides":[53],"a":[54],"high-level":[55],"synthesis":[56],"field-highlighting":[59],"its":[60],"motivation,":[61],"conceptual":[62],"foundations,":[63],"methodological":[65],"taxonomy":[66],"rather":[67],"than":[68],"enumerating":[69],"individual":[70],"techniques.":[71],"We":[72,97],"organize":[73],"mechanistic":[74,114,163],"across":[76],"three":[77,87],"abstraction":[78],"layers\u2014":[79],"neurons":[80],",":[81,83,91,93],"circuits":[82],"algorithms":[85],"\u2014and":[86],"evaluation":[88],"perspectives:":[89],"behavioral":[90],"counterfactual":[92],".":[96],"further":[98],"discuss":[99],"representative":[100],"approaches":[101],"toolchains":[103],"enable":[105],"structural":[106],"analysis":[107],"modern":[109],"AI":[110],"systems,":[111],"outlining":[112],"bridges":[116],"theoretical":[117],"insights":[118],"with":[119],"practical":[120],"transparency.":[121],"Despite":[122],"rapid":[123],"progress,":[124],"challenges":[125],"persist":[126],"in":[127,171],"scaling":[128],"these":[129],"analyses":[130],"frontier":[132],"models,":[133],"resolving":[134],"polysemantic":[135],"representations,":[136],"establishing":[138],"standardized":[139],"benchmarks.":[141],"By":[142],"connecting":[143],"historical":[144],"evolution,":[145],"current":[146],"methodologies,":[147],"emerging":[149],"research":[150],"directions,":[151],"aims":[154],"provide":[156],"an":[157],"integrative":[158],"framework":[159],"for":[160],"understanding":[161],"can":[165],"support":[166],"transparency,":[167],"reliability,":[168],"governance":[170],"large-scale":[172],"AI.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-01-25T00:00:00"}
