© 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. 61902
    Prev
    Next
    INDEX
    Explanations

    my or some followed by a noun

    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
    好çľĭ
    -0.12
    éĻĤ
    -0.11
    ç§Ģ丽
    -0.10
    íĮ©
    -0.10
    åIJĦèĩªçļĦ
    -0.10
    ä¸Ĭçľĭ
    -0.10
    å¿ĥ缮ä¸Ń
    -0.09
    åģ¥åħ¨
    -0.09
    ç´łè´¨æķĻèĤ²
    -0.09
    -vars
    -0.09
    POSITIVE LOGITS
    .some
    0.09
    Nich
    0.08
    bib
    0.07
     Bib
    0.07
    åį·
    0.07
    为äºĨæĽ´å¥½
    0.07
    @example
    0.07
    æĪijåıªæĺ¯
    0.07
    ä¸įåİ»
    0.07
     Trim
    0.07
    Activations Density 0.985%

    No Known Activations