© 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. 44171
    Prev
    Next
    INDEX
    Explanations

    foreign and concluding words

    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
    æĪĴ
    -0.06
    beau
    -0.06
    ä¿¡
    -0.06
    éĺ³æĺ¥
    -0.05
    åIJ¬æĩĤ
    -0.05
    on
    -0.05
     mo
    -0.05
     bur
    -0.05
     &
    -0.05
     loss
    -0.05
    POSITIVE LOGITS
    æľĢåIJİåľ¨
    0.11
    Lastly
    0.10
     enfin
    0.10
    æľĢåIJİæĺ¯
    0.10
    สุà¸Ķà¸Ĺà¹īาย
    0.09
     ë§Īì§Ģë§īìľ¼ë¡ľ
    0.09
    æľĢåIJİçļĦ
    0.09
     schlieÃŁlich
    0.09
    æľĢå¾Įãģ«
    0.09
     Lastly
    0.09
    Activations Density 0.070%

    No Known Activations