© 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. 44648
    Prev
    Next
    INDEX
    Explanations

    data format syntax and parsing

    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
    mana
    -0.08
    tay
    -0.07
    badge
    -0.07
    лага
    -0.07
    à¹Ģà¸Ĺà¹Īา
    -0.07
    ïs
    -0.07
    èIJ¦ç»ķ
    -0.06
    allas
    -0.06
    louv
    -0.06
     vân
    -0.06
    POSITIVE LOGITS
     parsing
    0.08
    éĢļåĪĻ
    0.08
     grammar
    0.08
    /win
    0.08
     parsers
    0.08
    etzen
    0.07
     whitespace
    0.07
     standards
    0.07
     parser
    0.07
    ä¸įæİ¥åıĹ
    0.07
    Activations Density 0.027%

    No Known Activations