© 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. 44836
    Prev
    Next
    INDEX
    Explanations

    discussion and conversation

    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
    åįĩåĪĿ
    -0.08
    åĬŀäºĨ
    -0.08
     preoc
    -0.08
    ble
    -0.07
    MainFrame
    -0.07
    _repr
    -0.07
    åĩºæĪĺ
    -0.07
     moj
    -0.07
     spenn
    -0.07
    RIX
    -0.07
    POSITIVE LOGITS
     discussion
    0.09
    讨论
    0.09
    æıIJéĹ®
    0.09
    å¼ķ导
    0.08
     Discussion
    0.08
    discussion
    0.08
     discuss
    0.08
    大å±ıå¹ķ
    0.08
    çıŃä¼ļ
    0.08
     обÑģ
    0.08
    Activations Density 0.013%

    No Known Activations