© 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. 683
    Prev
    Next
    INDEX
    Explanations

    division or ratio

    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
    èĩ´è¿ľ
    -0.07
    黯
    -0.07
    Pag
    -0.07
    pag
    -0.07
    大åĬŁ
    -0.06
    psilon
    -0.06
    lai
    -0.06
    *Math
    -0.06
    广åıĹ
    -0.06
    uffy
    -0.06
    POSITIVE LOGITS
    yton
    0.08
    个èµŀ
    0.07
    dale
    0.07
     dividing
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
     divide
    0.07
     division
    0.07
    åħ¶ä»ĸ类似éĹ®é¢ĺ
    0.07
    åĪĨ许
    0.07
    ä¸īæ°´
    0.07
    Activations Density 0.006%

    No Known Activations