© 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. 9517
    Prev
    Next
    INDEX
    Explanations

    format, formatted, structure

    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
    .baidu
    -0.08
     kingdom
    -0.07
    ×Ļק
    -0.07
    rim
    -0.07
    indh
    -0.07
    -picker
    -0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.06
    andong
    -0.06
    ä¾µçĬ¯äºĨæĤ¨çļĦ
    -0.06
    ptes
    -0.06
    POSITIVE LOGITS
    format
    0.07
     formatted
    0.07
    _plural
    0.06
    Äĥt
    0.06
    æł¼å¼ı
    0.06
     format
    0.06
    姿
    0.06
     plat
    0.06
    amm
    0.06
    creens
    0.06
    Activations Density 0.003%

    No Known Activations