© 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. 48899
    Prev
    Next
    INDEX
    Explanations

    which apps or items

    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
    ä¸įæŃ¢
    -0.09
    aut
    -0.09
    ../../
    -0.08
    anja
    -0.08
    人æ°ijæĹ¥æĬ¥
    -0.08
    coal
    -0.08
     Rut
    -0.08
    纨
    -0.08
    ØŃÙĨ
    -0.08
    ÎĻ
    -0.08
    POSITIVE LOGITS
    soever
    0.16
    /how
    0.12
     aspects
    0.10
    ç±»åŀĭçļĦ
    0.10
    å®ļå¾ĭ
    0.10
    cosa
    0.10
    æĸ¹éĿ¢çļĦ
    0.09
     portion
    0.09
    /all
    0.09
     Kob
    0.09
    Activations Density 0.018%

    No Known Activations