© 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. 43982
    Prev
    Next
    INDEX
    Explanations

    ratio or proportion

    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
    earned
    -0.08
     veloc
    -0.08
    oen
    -0.07
    åľ¨æİ¥åıĹ
    -0.07
    WithPath
    -0.07
     sval
    -0.07
    omon
    -0.07
    ãĤ¢ãĤ¤
    -0.06
    åİ
    -0.06
    åĬ¨ä¸įåĬ¨
    -0.06
    POSITIVE LOGITS
     dÆ°
    0.11
    éħįæ¯Ķ
    0.11
     ratio
    0.11
    æ¯Ķä¾ĭçļĦ
    0.10
    æ¯Ķä¾ĭ
    0.10
    è¿ĩéĩı
    0.10
     Ratio
    0.10
     ratios
    0.10
    ratio
    0.09
    失衡
    0.09
    Activations Density 0.030%

    No Known Activations