© 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. 40337
    Prev
    Next
    INDEX
    Explanations

    university.edu.cn acad epfl cn

    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
    为é¢ĺ
    -0.08
    åĭ¤åĭ¤æģ³æģ³
    -0.08
    ä¸ĭè½½æĬ¥åijĬ
    -0.08
    æİĴè¡Įæ¦ľåįķ
    -0.08
     poš
    -0.08
    å¹´åģĩ
    -0.08
    å·¥åķĨ注åĨĮåı·
    -0.08
    ç»ıçIJĨæĭĽèģĺ
    -0.08
    ronym
    -0.08
    ĴĪ
    -0.08
    POSITIVE LOGITS
    æĸ°ä¸ŃåĽ½
    0.08
    äºķ
    0.07
    æĪIJ
    0.07
    å¿Ĺ
    0.07
    æİ¥åĬĽ
    0.07
    åıģ
    0.06
    丼
    0.06
    ç§ijæĬĢ
    0.06
    China
    0.06
    >
    0.06
    Activations Density 0.002%

    No Known Activations