{"total":36,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2505.22483","title":"A Closer Look at Multimodal Representation Collapse","created":"2025-05-28","cited_by_count":28,"area":null},{"id":"2211.09169","title":"Engineering Monosemanticity in Toy Models","created":"2022-11-16","cited_by_count":13,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2504.08842","title":"Towards Combinatorial Interpretability of Neural Computation","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2510.11709","title":"Adversarial Attacks Leverage Interference Between Features in Superposition","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2507.09937","title":"Memorization Sinks: Isolating Memorization during LLM Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2501.06141","title":"Emergent Symbol-like Number Variables in Artificial Neural Networks","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2510.04500","title":"Expand Neurons, Not Parameters","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2511.06516","title":"You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2410.20161","title":"Causal Abstraction in Model Interpretability: A Compact Survey","created":"2024-10-26","cited_by_count":2,"area":null},{"id":"2502.20130","title":"QPM: Discrete Optimization for Globally Interpretable Image Classification","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.00928","title":"Superposition in Graph Neural Networks","created":"2025-08-31","cited_by_count":2,"area":null},{"id":"2603.10771","title":"Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2608.27540","title":"Towards a mathematical theory of superposition","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2410.06235","title":"Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2507.09816","title":"Compressed Computation: Dense Circuits in a Toy Model of the Universal-AND Problem","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2603.00270","title":"LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2605.02234","title":"Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.03990","title":"Neuron Populations Exhibit Divergent Selectivity with Scale","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2406.18926","title":"Fine-tuned network relies on generic representation to solve unseen cognitive task","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2506.21624","title":"DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2601.07411","title":"SCALPEL: Selective Capability Ablation via Low-rank Parameter Editing for Large Language Model Interpretability Analysis","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36455","title":"Emergent phases of superposition: from partial to full representation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}