© 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. 7359
    Prev
    Next
    INDEX
    Explanations

    followed by just, on, add

    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
    å¨
    -0.07
    ern
    -0.07
    -toggler
    -0.07
    ellar
    -0.07
    ç»
    -0.07
    REAM
    -0.07
    æŬ
    -0.07
    cheduler
    -0.07
    otron
    -0.07
    ıģ
    -0.07
    POSITIVE LOGITS
    人æĿ¥è¯´
    0.07
    brook
    0.07
    强çļĦ
    0.07
     ÐŁÐ»ÑİÑģ
    0.07
    anch
    0.07
     Laz
    0.07
    zion
    0.07
    esco
    0.07
    ημα
    0.06
    /MIT
    0.06
    Activations Density 0.006%

    No Known Activations