© 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. 35028
    Prev
    Next
    INDEX
    Explanations

    coefficient of variation ratios

    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
    dene
    -0.08
    æĺİçıł
    -0.07
    perimental
    -0.07
    +')
    -0.07
    ,status
    -0.07
    çļĦ人们
    -0.07
    溪åİ¿
    -0.07
    ulp
    -0.07
    çļĦæľĭåıĭ们
    -0.07
    лÑıм
    -0.07
    POSITIVE LOGITS
    ä¿¡
    0.08
    æĬ¬å¤´
    0.08
    æĭī
    0.07
    æ¯Ķä¾ĭ
    0.07
    åĬ¨
    0.07
    æħ¢
    0.07
     ratios
    0.07
    åĪĨ段
    0.07
     ratio
    0.07
    isson
    0.07
    Activations Density 0.006%

    No Known Activations