© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26516
    Prev
    Next
    INDEX
    Explanations

    ratio, index, coefficient, BMI, PI

    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
    ä¸Ģå®ļéĩıçļĦ
    -0.07
    amount
    -0.07
    约åįł
    -0.07
     amounts
    -0.07
    åĨ·çļĦ
    -0.07
     Becker
    -0.07
    sizeof
    -0.07
    iro
    -0.07
     soc
    -0.06
    åįł
    -0.06
    POSITIVE LOGITS
    åĢ¼çļĦ
    0.10
    åĢ¼
    0.10
    åĢ¼ä¸º
    0.09
    æ¯ĶåĢ¼
    0.09
     ratio
    0.09
    ratio
    0.09
     Ratio
    0.09
    åĢ¼æĺ¯
    0.09
    åĢ¤
    0.08
     ratios
    0.08
    Activations Density 0.089%

    No Known Activations