© 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. 18642
    Prev
    Next
    INDEX
    Explanations

    book and picture related words

    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
    带走
    -0.09
    lest
    -0.09
    pit
    -0.09
    åĮª
    -0.09
    meg
    -0.09
    صة
    -0.08
    lijk
    -0.08
    otta
    -0.08
     давно
    -0.08
    incy
    -0.08
    POSITIVE LOGITS
    æĭį
    0.09
    åľ°éģĵ
    0.09
    è¾¹å¢ĥ
    0.09
    éĥ¨åī¯
    0.09
    忸
    0.09
    路边
    0.08
    ä¸įä½³
    0.08
    åĿıäºĨ
    0.08
    纳æĸ¯
    0.08
    ç¬ij容
    0.08
    Activations Density 0.001%

    No Known Activations