© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20831
    Prev
    Next
    INDEX
    Explanations

    version, server, service, browser

    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
    èįīæł¹
    -0.08
    鼶åĶ®ä»·
    -0.08
     intuit
    -0.08
    Ùĥات
    -0.08
    å¿«ä¹IJåľ°
    -0.08
    ÚĨار
    -0.08
    sez
    -0.07
     Pancasila
    -0.07
    æ´»åĬ¨å¼Ģå±ķ
    -0.07
     vivid
    -0.07
    POSITIVE LOGITS
    严èĤĥ
    0.09
    æĹłåij³
    0.09
    书éĿ¢
    0.09
     cidd
    0.08
    çIJĨæĢ§
    0.08
    ono
    0.08
    æĹłå£°
    0.07
    åŃ¦æľ¯
    0.07
    åĨ·éĿĻ
    0.07
    严谨
    0.07
    Activations Density 0.673%

    No Known Activations