© 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. 11186
    Prev
    Next
    INDEX
    Explanations

    compounds 4a, 6d, 6e, 6h, 6k

    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¸įåħ¥
    -0.07
    ä¸įå±¥è¡Į
    -0.07
    ooky
    -0.06
    å½±éŁ¿
    -0.06
    奥åĪ©
    -0.06
    å½±åĵį
    -0.06
    åIJĥ好
    -0.06
    éĿ¢åĮħ
    -0.06
    红楼
    -0.06
     >>=
    -0.06
    POSITIVE LOGITS
    æľīæīĢæĢĿ
    0.08
    家åįıä¼ļ
    0.08
    æŁIJäºĽ
    0.07
    æ¹ĥ
    0.07
    niest
    0.07
     Satur
    0.07
     Certa
    0.07
    boxed
    0.07
    ç¦ģä¸įä½ı
    0.06
    eden
    0.06
    Activations Density 0.110%

    No Known Activations