A faithful activation reader should notice when the thing asked about is absent from its activations and should know which of its statements the activations sup
Diagnosing a model's reasoning with an Activation Oracle (AO) requires reading trajectory-specific facts, not just problem-level gist. We test whether AO reader
We compare Activation Oracle (AO) readers of Qwen3-8B with matched text readers and donor activations in two settings. On reasoning traces we count rollout-spec
What can an Activation Oracle reader say about a model's next step from one end-of-window activation, beyond the visible text? We test two Qwen3-8B readers (GRP
PersonaQA asks an activation reader for attributes a fine-tuned model stores for 100 personas but its context does not state. The adapted Qwen3-8B answers 93%;
PersonaQA asks an Activation Oracle (AO) reader for an attribute that a fine-tuned Qwen3-8B stores about a persona, from one residual state. The task's readers
A base-model text reader of a 50-token read window describes Qwen3-8B reasoning traces with more trace-specific claims than Activation Oracle (AO) readers, but
Difference readers decode what a fine-tune was trained to do from its residual state minus a reference. We ask whether such readouts track the behaviour or the
Can a short training run make Activation Oracle readers forecast what a model writes next, beyond what the visible text gives? Earlier work found that two Qwen3