© 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. 21313
    Prev
    Next
    INDEX
    Explanations

    git bundle, members name, sentence rings

    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
    vas
    -0.07
    -eslint
    -0.07
    æŁ»
    -0.06
    usher
    -0.06
    IES
    -0.06
    ept
    -0.06
    ELS
    -0.06
    审
    -0.06
    åħĭæĸ¯
    -0.06
    sov
    -0.06
    POSITIVE LOGITS
    cina
    0.07
    lach
    0.07
    ä½ķä¸į
    0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    0.07
    ä¸īåħ«
    0.07
     Chau
    0.07
    /AFP
    0.07
    è¿ĶåĽŀé¦ĸ页
    0.06
    å¼Ģå¼ł
    0.06
    ä»ĸçŁ¥éģĵ
    0.06
    Activations Density 0.020%

    No Known Activations