© 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. 58834
    Prev
    Next
    INDEX
    Explanations

    governing equations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¬ãĥĥ
    -0.09
    æĸ°åĬłåĿ¡
    -0.08
    à¸Ļวà¸Ļ
    -0.08
    éįĬ
    -0.07
    pread
    -0.07
     mancan
    -0.07
    راÙĥ
    -0.07
    æĿ·
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    phia
    -0.07
    POSITIVE LOGITS
     equations
    0.11
     governing
    0.09
    æĸ¹ç¨ĭ
    0.08
     equation
    0.08
    -derived
    0.07
     describing
    0.07
     constraints
    0.07
    Written
    0.07
     Written
    0.07
     laws
    0.07
    Activations Density 0.042%

    No Known Activations