© 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. 7784
    Prev
    Next
    INDEX
    Explanations

    today's context

    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
    heb
    -0.08
     esqu
    -0.08
    alez
    -0.07
    åݻ年
    -0.07
     damals
    -0.07
    ãi
    -0.07
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    ÄĽj
    -0.07
     Legislat
    -0.07
    ickers
    -0.07
    POSITIVE LOGITS
    -day
    0.09
    çļĦä»Ĭ天
    0.09
    adays
    0.08
    绪
    0.08
    çļĦæĪij们
    0.08
     meg
    0.07
    ä¸įè¿ĩåľ¨
    0.07
    çĬ¶åĨµ
    0.07
     modern
    0.07
    day
    0.07
    Activations Density 0.133%

    No Known Activations