© 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. 52133
    Prev
    Next
    INDEX
    Explanations

    special characters in code and math

    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
    åķ¦åķ¦
    -0.07
    points
    -0.07
    æı©
    -0.06
     lòng
    -0.06
     Gale
    -0.06
    igli
    -0.06
    åĢĴ
    -0.06
    meg
    -0.06
    éĩĮè¾¹
    -0.06
    æĮĩ导åijĺ
    -0.06
    POSITIVE LOGITS
    æģ¯
    0.08
    compiler
    0.07
    ANDOM
    0.07
    cesi
    0.07
    èIJĥ
    0.07
    à¹Īาà¸ĩ
    0.07
    uckle
    0.07
    reno
    0.07
    ucch
    0.07
    åħ¶ä¸İ
    0.07
    Activations Density 0.007%

    No Known Activations