© 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. 44500
    Prev
    Next
    INDEX
    Explanations

    code syntax with 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
    åıijæĮ¥èĩªå·±çļĦ
    -0.08
    udo
    -0.08
    ìĹħìĿĦ
    -0.08
    è»Ĵ
    -0.07
    好åij¢
    -0.07
    å®ľ
    -0.07
    à¤ķर
    -0.07
    çľĭä¸Ĭ
    -0.07
    ä»İè½»
    -0.07
    lys
    -0.07
    POSITIVE LOGITS
    Integral
    0.08
     Integral
    0.08
    integral
    0.07
    _integral
    0.07
     integral
    0.07
    urgo
    0.07
    åįģåŃĹ
    0.06
     INTEGR
    0.06
    æľīå¤ļ
    0.06
    pager
    0.06
    Activations Density 0.002%

    No Known Activations