© 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. 63642
    Prev
    Next
    INDEX
    Explanations

    code examples and explanations

    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
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.11
     thereof
    -0.09
    è¿Ļç§įä¸ľè¥¿
    -0.08
    ror
    -0.08
    راÙĨ
    -0.08
    ä¹ĭé«ĺ
    -0.08
    roud
    -0.08
    gst
    -0.08
    ities
    -0.07
    à¸Ļัà¹īà¸Ļ
    -0.07
    POSITIVE LOGITS
    даÑĩа
    0.08
    ast
    0.07
     an
    0.07
    为ä»Ģä¹Īåij¢
    0.07
    an
    0.07
    i
    0.07
    ä¸įåı¯èĥ½çļĦ
    0.07
     곧
    0.07
     a
    0.06
    adays
    0.06
    Activations Density 0.013%

    No Known Activations