© 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. 6974
    Prev
    Next
    INDEX
    Explanations

    Parkinson's, Companies, DPS, coverage, Stream, poll, IllegalArgumentException

    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
    Negative Logits
     übrigens
    -0.09
    è¿Ŀåıįä¸Ĭè¿°
    -0.08
     bowiem
    -0.07
    ä¹ĭæīĢ以
    -0.07
    éģ¿åħįåĽł
    -0.07
    å¤ļåIJĥä¸ĢäºĽ
    -0.07
    oppi
    -0.07
    ä¿ĿæĮģèī¯å¥½çļĦ
    -0.07
     zade
    -0.07
     tellement
    -0.07
    POSITIVE LOGITS
     ê·¸ë¦¬ê³ł
    0.08
    **|
    0.08
    %C
    0.07
    åį´èĥ½
    0.07
    ]+$
    0.07
    ä¸ĭåIJĮ
    0.07
    [J
    0.07
    .doc
    0.07
    ä»ĸåį´
    0.07
    домо
    0.07
    Activations Density 3.934%

    No Known Activations