© 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. 11450
    Prev
    Next
    INDEX
    Explanations

    column plus literal

    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
    ÙģÙĦ
    -0.07
    èĤ¯
    -0.06
    erne
    -0.06
    æij©
    -0.06
    lung
    -0.06
    #/
    -0.06
    icata
    -0.06
    éĿ¢éĿ¢
    -0.06
     Mere
    -0.06
    úk
    -0.06
    POSITIVE LOGITS
    WEBPACK
    0.08
    -addons
    0.07
    ued
    0.07
    AndGet
    0.07
    cky
    0.07
    æĤ¨çİ°åľ¨çļĦä½įç½®
    0.07
    á»Ĺ
    0.07
    è°§
    0.07
    resents
    0.07
    ä¸įè¿ĺ
    0.07
    Activations Density 0.128%

    No Known Activations