© 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. 60378
    Prev
    Next
    INDEX
    Explanations

    where/which is typically

    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
    itung
    -0.09
    don
    -0.08
    è¢
    -0.08
    åIJijèį£
    -0.08
    nil
    -0.07
    dont
    -0.07
    Òº
    -0.07
    Å¡Å¥
    -0.07
    losures
    -0.07
    yy
    -0.07
    POSITIVE LOGITS
    çļĦèĩªå·±
    0.07
    usul
    0.06
    ipasi
    0.06
    elere
    0.06
    纲
    0.06
    kreis
    0.06
    åĮ£
    0.06
    otope
    0.06
    æľĢ好æĺ¯
    0.06
    öre
    0.06
    Activations Density 0.009%

    No Known Activations