© 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. 18584
    Prev
    Next
    INDEX
    Explanations

    email/article beginnings

    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
    ishing
    -0.09
    wich
    -0.08
    ä¸Ĭä¸ĢæĿ¡
    -0.08
    idian
    -0.07
    zyn
    -0.07
    pty
    -0.07
    htub
    -0.07
    壮
    -0.07
    papers
    -0.07
    ánÃŃ
    -0.07
    POSITIVE LOGITS
    .opend
    0.07
    已累计
    0.07
    ä¸įæĶ¾å¼ĥ
    0.07
    帷å¹ķ
    0.07
    ç¨ĭ度çļĦ
    0.07
    æĪIJ绩çļĦ
    0.07
    ights
    0.07
    ÏģεÏħ
    0.06
     extern
    0.06
    ç«Ńè¯ļ
    0.06
    Activations Density 0.018%

    No Known Activations