© 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. 34992
    Prev
    Next
    INDEX
    Explanations

    derivative of mathematical expressions

    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
    ÑĮÑİ
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    éļĪ
    -0.07
    ymb
    -0.07
    utre
    -0.06
    转载请
    -0.06
    人ä¸ĸ
    -0.06
    utta
    -0.06
    人æĦı
    -0.06
    ce
    -0.06
    POSITIVE LOGITS
    åĻľ
    0.09
    urgi
    0.08
    rap
    0.08
    Ỿ
    0.07
    伦
    0.07
    rawat
    0.07
    ç³»ç»Łåľ¨
    0.07
    .compress
    0.07
     oneself
    0.07
    ontan
    0.07
    Activations Density 0.045%

    No Known Activations