© 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. 37486
    Prev
    Next
    INDEX
    Explanations

    operators and punctuation in code

    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
    acson
    -0.07
    scss
    -0.07
    inki
    -0.07
    ugen
    -0.07
    é£ŀ
    -0.06
    èį¤
    -0.06
    oyo
    -0.06
    ksz
    -0.06
    AWN
    -0.06
    inke
    -0.06
    POSITIVE LOGITS
    籽油
    0.07
    éĻµåİ¿
    0.07
    丽ä¸Ŀ
    0.07
    /OR
    0.07
    ç®Ģ称
    0.06
    ä¸įå°ijç½ijåıĭ
    0.06
    Ùĭ
    0.06
    ergestellt
    0.06
     itself
    0.06
    丽èİİ
    0.06
    Activations Density 0.141%

    No Known Activations