© 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. 16351
    Prev
    Next
    INDEX
    Explanations

    error or ok checks

    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
    è¿ĩçĶŁæĹ¥
    -0.08
    ä¸ŃåŃĹ
    -0.08
    æ·±åĪ»é¢Ĩä¼ļ
    -0.08
    éļıå¤Ħåı¯è§ģ
    -0.07
    éľĨ
    -0.07
    README
    -0.07
    å°ģ顶
    -0.07
    ais
    -0.07
    æĺ¥æļĸ
    -0.07
    æľĢæĸ°æĽ´æĸ°
    -0.07
    POSITIVE LOGITS
    èĭ¥
    0.11
    æĺ¯åIJ¦ä¸º
    0.11
    åĨ³å®ļæĺ¯åIJ¦
    0.11
    æĺ¯åIJ¦
    0.10
    èĭ¥æľī
    0.10
     Ùģإذا
    0.10
    æĺ¯åIJ¦æĺ¯
    0.10
    èĭ¥æĺ¯
    0.09
    æĺ¯åIJ¦æľī
    0.09
    æĺ¯åIJ¦åľ¨
    0.09
    Activations Density 0.229%

    No Known Activations