© 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. 20244
    Prev
    Next
    INDEX
    Explanations

    numbers or code

    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
    воÑĢ
    -0.08
    Ñĸб
    -0.08
    asaan
    -0.08
    isso
    -0.08
    รม
    -0.08
    æĪIJåĪĨæĺ¯
    -0.08
    ิว
    -0.08
    ç½Ĺæĭī
    -0.08
    åŁİ西
    -0.08
    äºĨä¸Ģå®ļ
    -0.08
    POSITIVE LOGITS
    æĪij们è¿ĺåı¯ä»¥
    0.07
    æīĢ
    0.07
     actually
    0.07
    T
    0.06
    æĪij们
    0.06
    å®ŀéĻħä¸Ĭ
    0.06
    ç¡®ä¿ĿäºĨ
    0.06
    4
    0.06
    ç®Ĺ
    0.06
    à¹ĩà¸ĩ
    0.06
    Activations Density 0.053%

    No Known Activations