© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15322
    Prev
    Next
    INDEX
    Explanations

    listing points or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    -0.08
    "
    -0.07
    lest
    -0.06
    =
    -0.06
    翻身
    -0.06
    8
    -0.06
    s
    -0.06
    hr
    -0.06
    6
    -0.06
    (
    -0.06
    POSITIVE LOGITS
    stime
    0.08
    ানà§įত
    0.08
    à¸Ńืà¹Īà¸Ļ
    0.08
     поÑĥ
    0.08
    kezés
    0.08
    cesi
    0.08
     ÑĥÑģк
    0.08
    à²ķà³įಷ
    0.07
    ï¼ļ</
    0.07
    æĥ³æĸ¹
    0.07
    Activations Density 0.009%

    No Known Activations