© 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. 8460
    Prev
    Next
    INDEX
    Explanations

    squealing noise

    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
    éĥ¨åĪĨçļĦ
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.07
    lim
    -0.07
    éĥ¨åĪĨæĺ¯
    -0.07
    éģĻ
    -0.06
    ä¸ĢæŃ¥æŃ¥
    -0.06
    ï¾ŀ
    -0.06
    人æ°ijåħ±åĴĮåĽ½
    -0.06
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    -0.06
    çŁ¥çľĮ
    -0.06
    POSITIVE LOGITS
    ³
    0.08
    yt
    0.07
    æľĽè¿ľ
    0.07
    ابت
    0.07
    hear
    0.07
    hibition
    0.06
    éĻħ
    0.06
    ysis
    0.06
    æ©
    0.06
    æĸĩä¸Ń
    0.06
    Activations Density 0.005%

    No Known Activations