© 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. 25490
    Prev
    Next
    INDEX
    Explanations

    Explicit formulas

    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
    iale
    -0.08
    heb
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    æĥĬæĤļ
    -0.07
    odyn
    -0.07
    ucar
    -0.07
    erve
    -0.07
    è®
    -0.07
    ä»»
    -0.07
    è¨
    -0.07
    POSITIVE LOGITS
     
    0.07
     Mast
    0.06
    <h
    0.06
    Copy
    0.06
    ások
    0.06
    ´
    0.06
    鸵
    0.06
    ACA
    0.06
    mast
    0.06
     findings
    0.06
    Activations Density 0.050%

    No Known Activations