© 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. 54975
    Prev
    Next
    INDEX
    Explanations

    math notation with numbers

    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
     Gabrie
    -0.08
    /dir
    -0.08
    UDA
    -0.08
    å®ĥéĤ£
    -0.08
     Habib
    -0.08
    lica
    -0.08
    SES
    -0.08
    endr
    -0.07
    CTS
    -0.07
    =open
    -0.07
    POSITIVE LOGITS
     totals
    0.09
     total
    0.09
    æĢ»è®¡
    0.08
    åIJĪ计
    0.08
    åĬłèµ·æĿ¥
    0.08
     totaling
    0.08
    æĢ»çļĦ
    0.08
    åIJĪè¨Ī
    0.08
     Total
    0.07
    total
    0.07
    Activations Density 0.002%

    No Known Activations