© 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. 1722
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    缴æİ¥æĪĸéĹ´æİ¥
    -0.08
    åĿŀ
    -0.07
    estal
    -0.07
    _INITIALIZER
    -0.07
    ибо
    -0.07
    adh
    -0.07
    åĸľéĹ»
    -0.07
    гол
    -0.06
    lost
    -0.06
    omat
    -0.06
    POSITIVE LOGITS
    ashes
    0.07
    éģĵ
    0.07
    就对
    0.07
    天ä¹ĭ
    0.07
    çIJª
    0.06
    lj
    0.06
    ç¿İ
    0.06
    еÑģÑĮ
    0.06
    uned
    0.06
    天äºĨ
    0.06
    Activations Density 0.121%

    No Known Activations