© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51875
    Prev
    Next
    INDEX
    Explanations

    two kinds or types

    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
    wali
    -0.07
    kund
    -0.07
    èµ°è¿ĩäºĨ
    -0.07
    cese
    -0.06
    tien
    -0.06
    ä¹Łä¸įåĨį
    -0.06
    scy
    -0.06
    æµĴ
    -0.06
    ERE
    -0.06
    orna
    -0.06
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.09
     depending
    0.09
     tùy
    0.08
    éľĵ
    0.08
    è¿Ļä¸īç§į
    0.07
    ä¿Ŀç¨İåĮº
    0.07
    çŃīåħ¶ä»ĸ
    0.07
     dependendo
    0.07
    æĪªçĦ¶ä¸įåIJĮçļĦ
    0.07
    两ç§į
    0.07
    Activations Density 0.052%

    No Known Activations