© 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. 27612
    Prev
    Next
    INDEX
    Explanations

    chapter numbers

    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
    /not
    -0.09
    iss
    -0.09
    toa
    -0.09
    onta
    -0.09
    ç¥ŀ
    -0.08
    æ²Ļ
    -0.08
    fo
    -0.08
    ording
    -0.08
    ifik
    -0.08
    imbus
    -0.08
    POSITIVE LOGITS
     chapters
    0.11
    apters
    0.11
    ç«ł
    0.10
    ä¹ł
    0.09
    æľ«
    0.09
    第ä¸Ģç«ł
    0.09
    ç«łèĬĤ
    0.09
    ingleton
    0.09
    第ä¸ĢèĬĤ
    0.09
    第ä¸īèĬĤ
    0.09
    Activations Density 0.046%

    No Known Activations