© 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. 7206
    Prev
    Next
    INDEX
    Explanations

    table structure

    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
     {}).
    -0.08
    atch
    -0.08
     dét
    -0.07
    stal
    -0.07
    æĢ»ç»ĵåĩº
    -0.07
    ÏĦον
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
    æĢ»çļĦ
    -0.07
    numberOf
    -0.07
    asset
    -0.07
    POSITIVE LOGITS
    vais
    0.09
    horia
    0.07
    åĽłä¸ºæĺ¯
    0.06
    åĿĽ
    0.06
    upes
    0.06
    ноÑģ
    0.06
    滨æ¹ĸ
    0.06
    çľĭåľ¨çľ¼éĩĮ
    0.06
    à¤ľà¤°
    0.06
    éľĦ
    0.06
    Activations Density 0.009%

    No Known Activations