© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8919
    Prev
    Next
    INDEX
    Explanations

    plays shakespearean tragedies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oul
    -0.10
    èķ²
    -0.09
    çĦĻ
    -0.09
    éĺħè§Ī
    -0.09
    èªĬ
    -0.09
    .Creator
    -0.09
    为人
    -0.09
     dom
    -0.08
    çī²
    -0.08
    èĽĩ
    -0.08
    POSITIVE LOGITS
    è¿ĩåĪĨ
    0.10
    noon
    0.09
    andon
    0.09
    å¿ĺ
    0.08
    èĪį
    0.08
    å°ıæľĭåıĭ
    0.08
     Shuttle
    0.08
    åĩī
    0.08
    ansi
    0.08
    umo
    0.08
    Activations Density 0.012%

    No Known Activations