© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50344
    Prev
    Next
    INDEX
    Explanations

    division, ratio, and related operations

    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
    æŀķ头
    -0.08
    åºĬåŀ«
    -0.08
    osso
    -0.08
     shoulder
    -0.08
    å¯IJ
    -0.07
    æĥĬ天
    -0.07
    à®Łà¯įà®ļ
    -0.07
    大纲
    -0.07
    _codes
    -0.07
     Sleeping
    -0.07
    POSITIVE LOGITS
     ratios
    0.18
     ratio
    0.17
     Ratio
    0.16
    Ratio
    0.15
    ratio
    0.15
    æ¯ĶåĢ¼
    0.15
    _ratio
    0.14
     denominator
    0.13
    æ¯Ķçİĩ
    0.13
    _RATIO
    0.13
    Activations Density 0.055%

    No Known Activations