sparse autoencoder

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders EACL 2026 Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal AAAI 2026 Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction AAAI 2026 Constructing Interpretable Features from Compositional Neuron Groups ACL 2026 Controllable LLM Reasoning via Sparse Autoencoder-Based Steering ACL 2026 CRISP: Persistent Concept Unlearning via Sparse Autoencoders ACL 2026 Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026 Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs CVPR 2026 Difference in Task Performance on Sparse Speech Representations ACL 2026 Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models AAAI 2026 Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders EACL 2026 Evaluating Sparse Autoencoders for Monosemantic Representation EACL 2026 Evaluating the Impact of SAE-based Language Steering on LLM Performance EACL 2026 Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems AAAI 2026 Feature Drift: How Fine-Tuning Repurposes Representations in LLMs EACL 2026 Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations AAAI 2026 Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs AAAI 2026 From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models ACL 2026 From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? ACL 2026 HistLens: Mapping Idea Change across Concepts and Corpora ACL 2026 I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders AAAI 2026 Improving Sparse Autoencoder with Dynamic Attention CVPR 2026 Interpretable and Steerable Concept Bottleneck Sparse Autoencoders CVPR 2026 Interpretable Debiasing of Vision-Language Models for Social Fairness CVPR 2026 Interpretable Reward Model via Sparse Autoencoder AAAI 2026