Mechanistic Interpretability

Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

12 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-14

10 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-07

13 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Inside this field

Focused directions

434 papers

Latest in Mechanistic Interpretability

Browse all topics →
CardsList

  1. Emergent Latent-State Computation under Stochastic Volatility

    Jul 28, 2026Xiaoyu Huang, Lulu WangIntermediate Latent StatesLatent States

  2. KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability

    Jul 27, 2026Krithi Shailya, Ananya Lakshmi Ravi, Venkatanathan K. V. +4Medical Vision-Language ModelsExplainability

  3. LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings

    Jul 27, 2026Brittany Harbison, Ashok K. GoelPersonalityLarge Language Model Bias

  4. Do LLMs Know Their Vulnerable Scenarios?

    Jul 26, 2026Ziheng Peng, Huiqi Deng, Haoran Jing +5Large Language Model SafetyVulnerable Code

  5. LAWFUL: Law-Aligned Witness for Faithful Use of Latents

    Jul 26, 2026Kevin Chen, Kenneth W. Parker, Anish AroraModel InterpretabilityInductive Logic Programming

  6. Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation

    Jul 25, 2026Gonzalo A. RuzGene-Regulatory NetworksSurrogate Models

  7. Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

    Jul 25, 2026Dhruvil S, Fenil Sojitra, Ravirajsinh ChauhanMulti-Head Self-AttentionLatent Representation

  8. Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations

    Jul 24, 2026Kazi Kamruzzaman Rabbi, Md. Zami Al Zunaed Farabe, M. Sohel RahmanWeight-Only QuantizationQuantization

  9. Interior interpretability with attention rollout: contraction and propagation profiles in Transformers

    Jul 24, 2026Umberto Biccari, Qian Huang, Enrique ZuazuaTransformer AttentionModel Interpretability

  10. Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders

    Jul 23, 2026Pablo Santiago Potes Velasco, María del Mar García Matabanchoy, Óscar Julián Pérez Ladino +3Stereotype MitigationModel Interpretability

  11. Neural Feature Governance: Extending Atom Prevalence

    Jul 23, 2026Idris Karel Seunda Ekwe, Patrick Tenga Shako, Ernest Parfait FokouéBayesian Neural NetworksNeural Network

  12. Efficient and Interpretable Body-Based Emotion Recognition with Lightweight Temporal Convolutional Networks

    Jul 23, 2026Christian Arzate Cruz, Stefanos Gkikas, Houshyar AsadiTemporal Convolutional NetworksEmotion Recognition

  13. Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry

    Jul 22, 2026Jason Y. Hu, Ivan Higuera-Mendieta, Patrick Obin Sturm +1Atmospheric DynamicsWireless Foundation Models

  14. Scaling Interpretable Transformers with Parity Bottleneck Layers

    Jul 22, 2026Andrew Mack, Kraig Yuheng Tou, Mark Henry +2Transformer ArchitecturesModel Interpretability

  15. Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

    Jul 22, 2026Hiskias DingetoModel InterpretabilityLarge Language Model Decoder

  16. Interpretable Fuzzy Rule-Based Regression Extension for Ex-Fuzzy Library

    Jul 22, 2026Cayan Deniz Kucuktopana, Javier Fumanal-Idocin, Richard Pitts +1Interpretable ModelsExtended Version

  17. For What Reason? Interpreting Models' Encoding of Causation and Antithesis

    Jul 20, 2026Abhidip Bhattacharyya, Shira WeinCausal ReasoningNext-Token Prediction

  18. fSRD: Fuzzy Spectral Region Decomposition -- Automated Multi Operator Koopman Representations via an Adaptive Spectral Learning Architecture

    Jul 20, 2026Charles Bokor, Mark Cary, Denise Morrey +1Koopman OperatorChaos

  19. Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

    Jul 20, 2026Katarzyna Filus, Sebastian PokucińskiSemantic RepresentationsMechanistic Interpretability

  20. What does a Bayes-filtered transformer believe? A predictive Monte Carlo approach

    Jul 19, 2026Afiq Abdillah Effiezal Aswadi, Haotong Ma, Susan WeiPosteriorNext-Token Prediction

  21. Interpretable Machine Learning for Air Pollution and Respiratory Health Prediction: A Socioeconomic Subgroup Analysis

    Jul 19, 2026Maede Azani Hassan Abadi, Shouyi WangAir PollutionRespiratory Sound Classification

  22. RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planning

    Jul 18, 2026Nguyen Viet Tuan Kiet, Bui Dinh Pham, Duong Quoc Chinh +3Team FormationPrinciples

  23. Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs

    Jul 18, 2026Sharath Naganna, Tanvir Ahmed Sijan, Uddipta KalitaLarge Language Model PerformanceMechanistic Interpretability

  24. Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent

    Jul 17, 2026Sriram Balasubramanian, Soheil FeiziModel InterpretabilityModel Activations

  25. Interpretable and Calibrated Classification of Clinical Data Using Supervised Feature Binarization

    Jul 16, 2026Antony Garcia, Adrian Noriega, Gabrielle Britton +1Interpretable ModelsClinical

  26. Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

    Jul 16, 2026Jihoon Hong, Julian Skifstad, Qiyue Dai +2Efficient World-Action ModelWorld Models

  27. Transcoders for Investigating Deception in Language Models

    Jul 16, 2026Darius Lim, Nathan Leow, Xin Wei ChiaDeceptionMechanistic Interpretability

  28. Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions

    Jul 15, 2026Zachary IzzoMechanistic InterpretabilityTraining Data

  29. AIMO Interpretability Challenge

    Jul 15, 2026Michal Štefánik, Philipp Mondorf, Andreas Waldis +11Mathematical ReasoningOlympiad-Level Problem

  30. Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CT

    Jul 14, 2026Kwang-Hyun Uhm, Inhwa Son, Sung-Jea KoComputed Tomography Dataset3D Visual Grounding

  31. From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    Jul 14, 2026Ingmar Posner, Anson Lei, Bernhard SchölkopfScientific DiscoveryMechanistic Interpretability

  32. Understanding Structured Health Data through Interaction-Aware Mixture-of-Experts

    Jul 14, 2026Ji Hwan Park, Ying Ding, Tianjin GuoMixture-of-Experts ModelsMultimodal Clinical Data

  33. Designing Agent-Ready Websites for AI Web Agents: A Framework for Machine Readability, Actionability, and Decision Reliability

    Jul 13, 2026Said Elnaffar, Farzad RashidiWeb AgentsWeb

  34. Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

    Jul 13, 2026Zixiang Xu, Sixian Li, Huaxing Liu +4JudgesGrading

  35. Auditing the Risk Claims of Distributional Reinforcement Learning

    Jul 13, 2026Hari PrasadConditional-Value-At-RiskModel Interpretability

  36. All you need is SAMPAT

    Jul 10, 2026Jayadeva, Madhur AswaniModel InterpretabilityNeural Architectures

  37. Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders

    Jul 9, 2026Bendegúz Váradi, Zoltán KmettyImproving Sparse AutoencodersBert-Based Models

  38. Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

    Jul 9, 2026Amir AsiaeeModel InterpretabilityMechanistic Interpretability

  39. MLPTR-CC: Multi-label Pathology Test Recommendation using Classifier Chains and SHAP

    Jul 9, 2026Abu Rafe Md Jamil, Nayan MalakarDisease DetectionModel Interpretability

  40. Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

    Jul 8, 2026Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang +1Large Language Model JailbreaksLarge Language Model Performance

  41. Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

    Jul 8, 2026Thibaut Vidal, Julien FerryTrustworthy Artificial IntelligenceProvable Guarantees

  42. Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning

    Jul 8, 2026Pranav Sawant, Jakub KrejčíMechanistic InterpretabilityExplainable Artificial Intelligence

  43. ExplAIner: A Declarative Query Language for Explaining Classification Models

    Jul 7, 2026Marcelo Arenas, Pablo Barceló, Diego Bustamante +3XaiModel Interpretability

  44. Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

    Jul 7, 2026Evgenii Kuriabov, David Miller, Jia LiExplainabilityModel Interpretability

  45. Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models

    Jul 7, 2026Franz Motzkus, Sebastian BernhardAutonomous DrivingModel Interpretability

  46. Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer

    Jul 6, 2026Pedro Henrique da Costa Avelar, Le Ou-Yang, Min Wu +1Multi-Omic FrameworkModel Interpretability

  47. SHARC: SHAP-Based Interpretability in Machine Learning Risk Models for Regulatory Capital under ICAAP and CCAR

    Jul 6, 2026Ujjwala VadrevuRegulationShapley Value

  48. Noisy-Channel Minimum Bayes Risk Decoding

    Jul 6, 2026Yusuke Sakai, Hidetaka Kamigaito, Taro WatanabeChannel ModelingBayesian

  49. Latent Programming Horizons in Coding Agents

    Jul 6, 2026André Silva, Han Tu, Martin MonperrusCoding AgentsMechanistic Interpretability

  50. Unsupervised Features Mining via Activation Geometry

    Jul 5, 2026Amit LeVi, Elad David, Max FominModel ActivationsLarge Language Model Reasoning

  51. Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs

    Jul 4, 2026Kareem Elozeiri, Mervat Abassy, Omar Kallas +4DialectsArabic Natural Language Processing

  52. They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It

    Jul 3, 2026Alex KwonModel InterpretabilityReadout

  53. Individual Parameters in Weight-Sparse Transformers Appear Interpretable

    Jul 3, 2026Arnau Marin-Llobet, Stefan HeimersheimMechanistic InterpretabilityModel Weights

  54. Towards Robustness against Typographic Attack with Training-free Concept Localization

    Jul 2, 2026Bohan Liu, Wenqian Ye, Guangzhi Xiong +3Frozen Contrastive Language-Image Pre-Training Visual EncoderVision Transformer

  55. Fast Multi-dimensional Refusal Subspaces via RFM-AGOP

    Jul 2, 2026Thomas WinningerRefusalsReasoning Traces

  56. Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

    Jul 2, 2026Zhiren Gong, He Lu, Tiantong Wang +6AblationMechanistic Interpretability

  57. Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

    Jul 2, 2026Rodrigo Mendoza-SmithImproving Sparse AutoencodersLarge Language Model Decoder

  58. Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

    Jul 1, 2026Zihao Qi, Christopher EarlsQuantum Neural NetworksMany-Body Physics

  59. From Approximation to Emergence: A Theory of Deep Learning

    Jul 1, 2026Zhilin ZhaoOver-Parameterized Neural NetworksDeep Learning

  60. Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates

    Jul 1, 2026Elias Najarro, Ane Espeseth, Eleni Nisioti +2Model InterpretabilityEmergence