© 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. 56802
    Prev
    Next
    INDEX
    Explanations

    plane or line segments

    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
    sizeof
    -0.08
    uccio
    -0.08
    (sizeof
    -0.08
     sizeof
    -0.08
    tiba
    -0.07
    *sizeof
    -0.07
    æł¸
    -0.07
    åī¯éĥ¨éķ¿
    -0.07
     itib
    -0.07
    åıij表讨论
    -0.07
    POSITIVE LOGITS
     equation
    0.08
    æĸ¹ç¨ĭ
    0.07
    èħ°çº¿
    0.07
    å¾Ĺæ°´
    0.07
    лин
    0.07
     ken
    0.06
    γÏģαÏĨ
    0.06
    ustra
    0.06
     passing
    0.06
    itant
    0.06
    Activations Density 0.006%

    No Known Activations