© 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. 45061
    Prev
    Next
    INDEX
    Explanations

    units of measurement and rates

    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
    emi
    -0.08
    åľĺ
    -0.08
     Neutral
    -0.07
    ãĤĬè¿Ķ
    -0.07
     Plen
    -0.07
    ä¸Ģ路走æĿ¥
    -0.07
    еле
    -0.07
    .tem
    -0.07
    Neutral
    -0.07
    åĽ¢çļĦ
    -0.07
    POSITIVE LOGITS
    rul
    0.07
    upiter
    0.06
    æ¯ıç§Ĵ
    0.06
     Robotics
    0.06
    åijĬçŁ¥
    0.06
    \_
    0.06
    atro
    0.06
    .gov
    0.06
    \\
    0.06
    æ¯ı
    0.06
    Activations Density 0.008%

    No Known Activations