© 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. 19748
    Prev
    Next
    INDEX
    Explanations

    compact cameras, panel display, checkpoint Location, Plugins Enabled

    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
     appunto
    -0.11
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
     wÅĤaÅĽnie
    -0.07
    å°±æĺ¯è¿Ļ个
    -0.07
     "".
    -0.07
     weiterlesen
    -0.07
    ä¸įè¿ĩäºĨ
    -0.07
     }.
    -0.07
    }).
    -0.07
    .).
    -0.07
    POSITIVE LOGITS
    ,’”
    0.07
    .win
    0.07
    comes
    0.06
    äss
    0.06
     übrigens
    0.06
    åħ®
    0.06
    .asc
    0.06
    ÙİÙijت
    0.06
    èĭ±æĸĩåIJįåŃĹ
    0.06
    çļĦæĸ¹å¼ıæĿ¥
    0.06
    Activations Density 0.162%

    No Known Activations