© 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. 38783
    Prev
    Next
    INDEX
    Explanations

    in a context

    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
     YY
    -0.09
    ä¸ĩéĩĮ
    -0.09
    æīĢåľ¨
    -0.08
    _precision
    -0.08
    _accessible
    -0.08
    emean
    -0.08
     Infer
    -0.08
    èĥĮéĿ¢
    -0.08
    注æĦıåĬĽ
    -0.08
    OTES
    -0.08
    POSITIVE LOGITS
    ê¶Į
    0.10
    æİĮæݧ
    0.10
    ãģ£ãģ±
    0.09
    ogie
    0.09
    ä¸»å¼ł
    0.09
    usch
    0.09
    est
    0.09
    (always
    0.09
    çİ°åľº
    0.09
    ä¸Ģ个èģĮä¸ļ
    0.09
    Activations Density 0.049%

    No Known Activations