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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34204
    Prev
    Next
    INDEX
    Explanations

    put together

    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
    æĬľ
    -0.09
    éĤ¸
    -0.09
    steen
    -0.09
    嵩
    -0.09
    Ñħод
    -0.09
    usic
    -0.09
    .disk
    -0.09
    abetic
    -0.08
    odie
    -0.08
    uhl
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģ份
    0.14
    ä¸Ģå¥Ĺ
    0.11
    ä¸ĢæĶ¯
    0.11
    жал
    0.11
    è¿Ļå¥Ĺ
    0.10
    è¿ĻæĶ¯
    0.10
    好äºĨ
    0.09
    è¿Ļ对
    0.09
    äºĨä¸ĢäºĽ
    0.09
    èĢĮæĪIJ
    0.09
    Activations Density 0.010%

    No Known Activations