© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4829
    Prev
    Next
    INDEX
    Explanations

    slow, tedious, time-consuming

    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
    Negative Logits
    éªļ
    -0.08
    kori
    -0.08
     whatever
    -0.07
    kowski
    -0.07
    ¨
    -0.07
    setattr
    -0.07
    æĺ¾å¾ĹæĽ´åĬł
    -0.07
    æĿ¥è¶Ĭ
    -0.07
    chap
    -0.07
    éĻħ
    -0.07
    POSITIVE LOGITS
     unreliable
    0.07
    æĢİä¹ĪåĬŀ
    0.07
    otts
    0.07
    yota
    0.06
    念头
    0.06
    arate
    0.06
    ä¹Łä¸įè¡Į
    0.06
    enta
    0.06
    çļĦæĥ³æ³ķ
    0.06
    æĺ¯ä¸įåı¯
    0.06
    Activations Density 0.038%

    No Known Activations