© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    angle measurement

    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
     Vision
    -0.08
    åľ¨ä¸Ģå®ļ
    -0.08
    USTA
    -0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.07
     vision
    -0.07
    对ä¸ĢäºĽ
    -0.07
    rec
    -0.07
     konsul
    -0.07
    è·¯å°ıåѦ
    -0.07
    .accept
    -0.07
    POSITIVE LOGITS
    awat
    0.08
    йл
    0.08
    æģĭ
    0.07
    _hooks
    0.07
    æĺ¯ä¸İ
    0.07
    åģı离
    0.07
    èĥĮ离
    0.07
    æĪĢ
    0.07
    insky
    0.07
    Ñı
    0.07
    Activations Density 0.001%

    No Known Activations