© 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. 1945
    Prev
    Next
    INDEX
    Explanations

    Inc

    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
     полÑĥ
    -0.11
    ISM
    -0.09
    ä¸įäºĨ
    -0.09
    ãģ¹ãģį
    -0.09
    çľģæķĻèĤ²
    -0.09
    illard
    -0.08
    .sem
    -0.08
    æ³ł
    -0.08
    è¯Ĺåı¥
    -0.08
    zer
    -0.08
    POSITIVE LOGITS
    ä½Ļ家
    0.09
    ç®Ģ称
    0.09
    èĦIJ
    0.08
    æĸij
    0.08
    è´
    0.08
    oc
    0.08
    åī¯æĢ»ç»ıçIJĨ
    0.08
    俵
    0.08
    /vendors
    0.08
    è¿ĻæĿ¡
    0.08
    Activations Density 0.035%

    No Known Activations