© 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. 34832
    Prev
    Next
    INDEX
    Explanations

    wire, time, rate, replacement

    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
    EOS
    -0.07
    æľīä¸ĭåĪĹ
    -0.07
    ä¸Ĭè¿°
    -0.07
    &r
    -0.07
    &s
    -0.06
    åĥı
    -0.06
    quete
    -0.06
    quetes
    -0.06
    aff
    -0.06
    o
    -0.06
    POSITIVE LOGITS
     ross
    0.08
    èĥ½å¤ŁæľīæķĪ
    0.08
    åĪĨéĴŁåīį
    0.07
    çŃīä¼łç»Ł
    0.07
    åħĥåĴĮ
    0.07
    éĥ½æľīä¸įåIJĮçļĦ
    0.07
    éĺ¿å¼¥éĻĢ
    0.07
    个ä¸ĵä¸ļ
    0.07
    åįĩæľ¬
    0.07
    çŃīåIJĦ
    0.07
    Activations Density 0.001%

    No Known Activations