© 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. 22070
    Prev
    Next
    INDEX
    Explanations

    pronunciation guide

    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
    rement
    -0.09
    itious
    -0.08
    åıªåı¯æĥľ
    -0.08
    æĸĹå¿Ĺ
    -0.08
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.07
    itter
    -0.07
    æĢ§åľ°
    -0.07
    å·ŀç«ĭ
    -0.07
    æł©
    -0.07
    她表示
    -0.07
    POSITIVE LOGITS
    yssey
    0.07
    ught
    0.07
    yu
    0.07
    /name
    0.07
    ables
    0.07
    icrosoft
    0.07
    ãģ¹ãģį
    0.07
    åĴĮçIJĨ解
    0.07
    xic
    0.06
    speaker
    0.06
    Activations Density 0.002%

    No Known Activations