© 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. 13245
    Prev
    Next
    INDEX
    Explanations

    explanation for something

    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
    ä½Ĩä¸įè¦ģ
    -0.08
    èĻ½çĦ¶æ²¡æľī
    -0.08
    ä¸įå¿ĺ
    -0.07
    æĹłå¼Ĥè®®
    -0.07
    _INCLUDED
    -0.07
    ä¸įéĻIJ
    -0.07
    ãģªãģıãģ¦ãĤĤ
    -0.07
    dann
    -0.07
    ÃģNG
    -0.07
    ErrorMsg
    -0.07
    POSITIVE LOGITS
    å·²ç»ı没æľī
    0.10
     already
    0.09
    å·²ç»ıå¾Ī
    0.09
    æĹ¢ãģ«
    0.09
    å·²ç»ı
    0.09
    å·²ç»ıæľī
    0.08
    ãģĿãĤĤãģĿãĤĤ
    0.08
    å·²ç»ıå®Įåħ¨
    0.08
    éĥ½å·²ç»ı
    0.08
    å·²ç»ıæĺ¯
    0.08
    Activations Density 0.100%

    No Known Activations