© 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. 8201
    Prev
    Next
    INDEX
    Explanations

    let variable assignment

    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
    åĴĮ丰å¯ĮçļĦ
    -0.07
    æİ¥æĽ¿
    -0.07
    MT
    -0.07
     diluted
    -0.07
    plit
    -0.07
    ogli
    -0.06
    ethe
    -0.06
    éĵ¿
    -0.06
    st
    -0.06
    æĬ¥åijĬ书
    -0.06
    POSITIVE LOGITS
    uhi
    0.07
    aksa
    0.07
    ä¹ĭå·®
    0.07
    artal
    0.07
    webpack
    0.07
    å²Ľä¸Ĭ
    0.07
    å°ıèĤł
    0.07
    onus
    0.07
    åŃĺåľ¨çļĦ
    0.06
    amarin
    0.06
    Activations Density 0.011%

    No Known Activations