© 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. 57518
    Prev
    Next
    INDEX
    Explanations

    private entities

    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
     TÃłi
    -0.09
    å¤ľéĩĮ
    -0.08
    RequestBody
    -0.08
    uds
    -0.08
    ormal
    -0.08
    .liferay
    -0.08
    tracer
    -0.08
    åħļåĴĮæĶ¿åºľ
    -0.08
     Arch
    -0.08
    .AUTO
    -0.08
    POSITIVE LOGITS
    åķ
    0.09
    åĩłåĪĨ
    0.09
    ç¡
    0.09
    ply
    0.09
    izio
    0.08
    èIJ¥åĪ©
    0.08
    WindowState
    0.08
    ä¸įå®ļ
    0.08
    ç»ıèIJ¥æ´»åĬ¨
    0.08
    æ´»åĬ¨ä¸Ń
    0.08
    Activations Density 0.009%

    No Known Activations