© 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. 45955
    Prev
    Next
    INDEX
    Explanations

    .net/XML, .txt, .org

    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
    سÙħ
    -0.07
    .sourceforge
    -0.06
    ج
    -0.06
    ç§ijåѦåѦéĻ¢
    -0.06
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.06
    à¸ł
    -0.06
    Advertis
    -0.06
    _NC
    -0.06
    isFunction
    -0.06
     ÙģÙİØ¥
    -0.06
    POSITIVE LOGITS
    _GU
    0.09
    å¹´èıľ
    0.09
    èģĮä¸ļåѦéĻ¢
    0.09
    à¸Ķ
    0.09
    _tests
    0.08
    ì§ĢìĽIJ
    0.08
    _STOP
    0.08
    æ¸ī
    0.08
     Lò
    0.08
    Utils
    0.08
    Activations Density 3.122%

    No Known Activations