© 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. 31004
    Prev
    Next
    INDEX
    Explanations

    WITHOUT any

    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
    æĤ¨çİ°åľ¨çļĦä½įç½®
    -0.07
    kok
    -0.07
    avl
    -0.07
    èĢģå¸Ī们çļĦ
    -0.07
    оби
    -0.07
    onte
    -0.07
    боли
    -0.07
    illet
    -0.07
    ủng
    -0.07
    驳
    -0.07
    POSITIVE LOGITS
    æģ°æģ°
    0.07
    ä¸įè¡°
    0.06
    ucci
    0.06
    æĸ°åĬłåĿ¡
    0.06
     tradition
    0.06
    å§Ĩæĸ¯
    0.06
    LoginPage
    0.06
    ewriter
    0.06
    .deep
    0.06
    ZH
    0.06
    Activations Density 0.005%

    No Known Activations