© 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. 27230
    Prev
    Next
    INDEX
    Explanations

    putter, serve, cast

    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
    éĻ¢
    -0.09
    oze
    -0.09
    PA
    -0.09
    鹧
    -0.08
    ungle
    -0.08
     пом
    -0.08
    pa
    -0.08
     Thornton
    -0.08
    æľĢæĹ©çļĦ
    -0.08
    æ·±åĪ»çļĦ
    -0.08
    POSITIVE LOGITS
    åĿĬ
    0.09
    è¿Ļ项
    0.09
    éĩijåŃĹ
    0.09
    ì¡´
    0.09
    æݬ
    0.09
    é»»
    0.08
    \Eloquent
    0.08
    gles
    0.08
    letes
    0.08
    /sites
    0.08
    Activations Density 0.005%

    No Known Activations