© 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. 20240
    Prev
    Next
    INDEX
    Explanations

    quantities and units

    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
    éŨæĪ·
    -0.07
    ç«ĸ
    -0.07
     bÆ°á»Ľ
    -0.07
    _PARSE
    -0.07
    olest
    -0.06
    æĮºå¥½çļĦ
    -0.06
    hon
    -0.06
     Karn
    -0.06
    a
    -0.06
    éŁŃ
    -0.06
    POSITIVE LOGITS
    ìĶ©
    0.08
    (each
    0.08
    æ¯ıå¼ł
    0.08
    æ¯ıä¸Ģç§į
    0.08
    _each
    0.08
    ÑĤÑģÑı
    0.08
    each
    0.08
    æ¯ıä¸Ģ份
    0.08
    intes
    0.08
    ianya
    0.08
    Activations Density 0.134%

    No Known Activations