© 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. 4813
    Prev
    Next
    INDEX
    Explanations

    special characters and math notation

    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
     ÑıкобÑĭ
    -0.08
     Suj
    -0.07
    rint
    -0.07
    ByExample
    -0.07
    æīįè¡Į
    -0.07
    åīįèĢħ
    -0.07
    åħħå®ŀ
    -0.07
    LAT
    -0.07
    TagName
    -0.06
    MT
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥çľĭ
    0.09
    fors
    0.07
    aton
    0.07
    åı¯åĪĨ为
    0.07
    ÑĪон
    0.07
    -go
    0.07
    uvan
    0.07
    åı¯ä»¥åĪĨ为
    0.06
    ossid
    0.06
    çļĦä¸Ģ个éĩįè¦ģ
    0.06
    Activations Density 0.008%

    No Known Activations