© 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. 22440
    Prev
    Next
    INDEX
    Explanations

    detail: , thing: , point:

    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¸įä»ħåı¯ä»¥
    -0.08
    ä¸įä»ħä»ħ
    -0.08
    ä¸įä»ħèĥ½å¤Ł
    -0.07
    ä¸įä»ħ
    -0.07
    vey
    -0.07
    ä¸įä»ħèĥ½
    -0.07
    ÙĨت
    -0.07
    ä¸Ģå®ļä¸įä¼ļ
    -0.07
     simply
    -0.06
    æµĵ缩
    -0.06
    POSITIVE LOGITS
    åı¯åIJ¦
    0.09
    çļĦä¸ĢçĤ¹
    0.08
    alna
    0.07
    è¿ĺæľīä¸ĢçĤ¹
    0.07
    uard
    0.07
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.07
    管çIJĨæĸ¹éĿ¢
    0.07
    phia
    0.07
    UID
    0.07
    oze
    0.07
    Activations Density 0.052%

    No Known Activations