© 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. 8326
    Prev
    Next
    INDEX
    Explanations

    division and divisibility questions

    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
    èıı
    -0.07
    oup
    -0.06
    éħª
    -0.06
    andai
    -0.06
    èĿ¶éĺĢ
    -0.06
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.06
    ady
    -0.06
    дов
    -0.06
    æīĭ
    -0.06
    opc
    -0.06
    POSITIVE LOGITS
     Locator
    0.08
    ä¸ĢçŃ¹
    0.08
    åİĭä½İ
    0.07
    -addon
    0.07
    æĿ¥ä¹ĭä¸įæĺĵ
    0.07
     unlucky
    0.07
    anyi
    0.07
    lags
    0.07
     espet
    0.07
    æ±Łæµ·
    0.07
    Activations Density 0.012%

    No Known Activations