© 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. 55138
    Prev
    Next
    INDEX
    Explanations

    mathematical notation often followed by parentheses

    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
    æ¦ķ
    -0.07
    anser
    -0.07
    åľ°æĸ¹
    -0.07
    åľ°æĸ¹çļĦ
    -0.07
    à¸Ľà¸£à¸°à¸ģ
    -0.07
    orse
    -0.06
    åIJİæĤĶ
    -0.06
    iland
    -0.06
     Bari
    -0.06
    ÑĢий
    -0.06
    POSITIVE LOGITS
    aven
    0.08
    eram
    0.07
    ermo
    0.07
    éģĵåı£
    0.07
    bila
    0.07
    achel
    0.07
     '&'
    0.07
    Gro
    0.07
    svm
    0.07
    æĪijæĿ¥è¯´
    0.06
    Activations Density 0.040%

    No Known Activations