© 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. 50070
    Prev
    Next
    INDEX
    Explanations

    characters like Cat, Pearl, Kitty

    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
    æľīèĩ´
    -0.07
    åĩĿç¥ŀ
    -0.06
    ä¸Ĭä¹ĺ
    -0.06
    ä¹ĭç¾İ
    -0.06
    éĿĻå¿ĥ
    -0.06
    chau
    -0.06
    rpc
    -0.06
    rop
    -0.06
    æ£ĭ
    -0.06
     Sculpt
    -0.06
    POSITIVE LOGITS
     himself
    0.09
    形象åĴĮ
    0.09
    èĨ¨
    0.09
    åİĨéĻ©
    0.08
    ç¦ıæĺŁ
    0.08
    åĴĮä»ĸçļĦ
    0.08
    ä»ĸæĢ»æĺ¯
    0.08
    gai
    0.08
    è¶
    0.08
    yg
    0.08
    Activations Density 0.710%

    No Known Activations