Hands-On XAI Labs: companion notebooks for Hands-On Explainable AI

Thirteen executed Colab lab notebooks on interpreting, evaluating, and trusting large language models: feature attribution, attention analysis, probing, chain-of-thought faithfulness, mechanistic interpretability, behavioral auditing, explanation-aware training, and production explainability. Each lab runs on a free-tier Colab T4 GPU in twenty minutes or less, with fixed seeds. Companion repository for the book Hands-On Explainable AI (Hadi Mohammadi).