© 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. 22760
    Prev
    Next
    INDEX
    Explanations

    cycling race

    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
    æŃ£éĿ¢
    -0.09
    ä¸ĢæīĢ
    -0.08
    ward
    -0.08
    md
    -0.08
    elle
    -0.08
    æĺĮ
    -0.07
    hen
    -0.07
     Bars
    -0.07
     F
    -0.07
     H
    -0.07
    POSITIVE LOGITS
    duk
    0.11
    æĺİæĹ¥
    0.10
     diamond
    0.10
    ç»ķ
    0.09
    éĴ»çŁ³
    0.09
    LBL
    0.09
    羣å¿ĥ
    0.09
     zab
    0.09
     ÐŃÑĤ
    0.09
    (IService
    0.09
    Activations Density 0.015%

    No Known Activations