© 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. 37517
    Prev
    Next
    INDEX
    Explanations

    parsing numbers, php syntax, and code constructs

    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
     Kej
    -0.08
    å¿ħçŃĶ
    -0.08
    æ¸
    -0.08
    usercontent
    -0.07
    ç½ijç«Ļåľ°åĽ¾
    -0.07
    hamn
    -0.07
    cardo
    -0.07
    eldes
    -0.07
    ersions
    -0.07
    akh
    -0.07
    POSITIVE LOGITS
     nonexistent
    0.09
    åı¯ç¬ij
    0.07
    æĺ¯ä¸įåı¯èĥ½çļĦ
    0.06
    æĪĸ以ä¸Ĭ
    0.06
    ä¸įåŃĺåľ¨
    0.06
    çŃīåĿĩ
    0.06
    oga
    0.06
    ç¾İ人
    0.06
    andle
    0.06
    æŁı
    0.06
    Activations Density 0.003%

    No Known Activations