© 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. 63564
    Prev
    Next
    INDEX
    Explanations

    lived, way, sacrifice, evils, ruin, offer

    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
    é¹Ń
    -0.08
    å·´æĸ¯
    -0.08
    ugar
    -0.08
     tact
    -0.08
    pects
    -0.08
    perm
    -0.08
    dag
    -0.07
     mainstream
    -0.07
    诸å¦Ĥ
    -0.07
    ahead
    -0.07
    POSITIVE LOGITS
    .ylim
    0.10
    åĿ¨
    0.10
    ä¸Ģç§Ĵ
    0.10
    è¥ģ
    0.10
    æ»Ķ
    0.10
    å¤ļå¤ļ
    0.10
    颦
    0.09
    artial
    0.09
    å¥łåŁº
    0.09
    Ñĥв
    0.09
    Activations Density 0.054%

    No Known Activations