© 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. 4913
    Prev
    Next
    INDEX
    Explanations

    non-standard characters followed by 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
    Negative Logits
    é¢IJ
    -0.09
    akta
    -0.07
    aktan
    -0.07
    ç±ģ
    -0.07
    ฺ
    -0.07
    lotte
    -0.06
    ÌĢ
    -0.06
     Pres
    -0.06
    ssia
    -0.06
    Ùĭ
    -0.06
    POSITIVE LOGITS
    äºĭåįĬåĬŁåĢį
    0.07
    缸è¾ħ缸æĪIJ
    0.06
    itori
    0.06
    身临åħ¶å¢ĥ
    0.06
    ä¸įåı¯æĢĿè®®
    0.06
    éĩij鸡
    0.06
    oppi
    0.06
    çī©çļĦ
    0.06
    oger
    0.06
    à¸Ńà¸ģ
    0.06
    Activations Density 0.019%

    No Known Activations