arxiv:2606.10029
Nikita Balagansky
elephantmipt
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning
via Steering Vectors authored a paper 1 day ago
Steering LLM Reasoning Through Bias-Only Adaptation authored a paper 1 day ago
Train One Sparse Autoencoder Across Multiple Sparsity Budgets to
Preserve Interpretability and Accuracy