© 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. 15426
    Prev
    Next
    INDEX
    Explanations

    introduces qualifications or context

    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
    åIJ¸å¼ķæĽ´å¤ļçļĦ
    -0.07
    Ùģار
    -0.06
    ä¸įåħī
    -0.06
    ÑħÑĢо
    -0.06
    æĽ´ä¸įæĺ¯
    -0.06
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    -0.06
    ä¸Ģ缮
    -0.06
    åľ¨ä¸įåIJĮçļĦ
    -0.06
    å°¤åħ¶æĺ¯åľ¨
    -0.06
    è¿ĻæĹłçĸij
    -0.06
    POSITIVE LOGITS
    soever
    0.08
     btw
    0.08
    ä¹ĭ为
    0.07
    /mit
    0.07
    (er
    0.07
     же
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    à§įথ
    0.07
    !).
    0.06
    äºĨä¸Ģçķª
    0.06
    Activations Density 0.482%

    No Known Activations