WorkspaceBench gives interpretability tools 3,356 tests of model internals
Interpretability researchers can now test whether a tool is actually reading a model’s internal workspace, rather than guessing from its input, across 3,356 questions in 27 evaluation families. WorkspaceBench feeds an activation-to-text tool model states and checks answers on safety, logic, and multistep computation, including a separate test for hallucinated readings. It was built for Qwen-3.6-27B and is intended as a practical check for model-auditing tools.