© 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. 64344
    Prev
    Next
    INDEX
    Explanations

    definition of concepts

    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
    èµĸ
    -0.07
    anski
    -0.07
    æĹłä»¥
    -0.07
    èĭįèĿĩ
    -0.07
     ë¿IJ
    -0.07
    æĭ¿æĿ¥
    -0.07
    ãģ¤ãģĦãģŁ
    -0.07
    ä¿¡æģ¯è¿Ľè¡Į
    -0.07
    çļĦ大好
    -0.06
    æĹ¢çĦ¶
    -0.06
    POSITIVE LOGITS
    æĺ¯æĮĩåľ¨
    0.10
    ìĿ´ëŀĢ
    0.09
    æĺ¯æĮĩ
    0.09
    æĮĩçļĦæĺ¯
    0.08
    å°±æĺ¯æĮĩ
    0.08
    说çļĦæĺ¯
    0.07
    æľ¬åĬŀæ³ķ
    0.07
     (âĢ¦)
    0.07
    å½»
    0.07
    åįĹéŨ
    0.06
    Activations Density 0.028%

    No Known Activations