{"total":22,"rows":[{"id":"2601.08331","title":"CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark","created":"2026-01-13","cited_by_count":12,"area":null},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2504.15471","title":"Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2505.17630","title":"Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2509.08592","title":"Interpretability as Alignment: Making Internal Understanding a Design Principle","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2607.18921","title":"Circuit Claims Depend on What Is Extracted and How It Is Compared","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2506.22740","title":"Explanations are a Means to an End: Decision Theoretic Explanation Evaluation","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2602.23179","title":"Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.16023","title":"Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2602.11091","title":"Can Large Language Models Make Everyone Happy?","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.08192","title":"Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.12299","title":"GKnow: Measuring the Entanglement of Gender Bias and Factual Gender","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2609.00753","title":"How Do Language Models Choose Between Context and Memory?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13072","title":"MAxBench: A Multinomial Concept Recovery Benchmark","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.32818","title":"When Can First-Order Models of Fine-Tuning Bound Forgetting?","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.12737","title":"Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13018","title":"FlyHack: Stress-Testing Mechanistic Claims in a Connectome-Constrained Visual Model","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}