© 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. 43635
    Prev
    Next
    INDEX
    Explanations

    .Contains or membership

    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
    ä¸Ģ天天
    -0.09
     paired
    -0.07
    InBackground
    -0.07
    æģ¢å¤įæŃ£å¸¸
    -0.06
    æģ¢å¤įåĪ°
    -0.06
     Compte
    -0.06
    xee
    -0.06
     ÙħجتÙħع
    -0.06
    Disconnected
    -0.06
    èĢĮéļıçĿĢ
    -0.06
    POSITIVE LOGITS
     пÑĢинадлежноÑģÑĤи
    0.09
    足ä¸įåĩº
    0.08
    membership
    0.08
    交éĽĨ
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    .contains
    0.07
    ä¸İ该
    0.07
    缴æİ¥æĬĬ
    0.07
     membership
    0.07
    .Contains
    0.07
    Activations Density 0.032%

    No Known Activations