© 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. 62225
    Prev
    Next
    INDEX
    Explanations

    S.E.2d

    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
    ó
    -0.07
    奥
    -0.07
    WB
    -0.07
    มห
    -0.07
     microscopic
    -0.07
    RM
    -0.07
    çģ«èĬ±
    -0.06
    åĩ¡
    -0.06
    éĻ¤åİ»
    -0.06
    æ°ijçĶ¨
    -0.06
    POSITIVE LOGITS
    ICODE
    0.08
    é¢IJ
    0.07
    lda
    0.07
    ibra
    0.07
    ä¸Ģç¯ĩæĸĩç«ł
    0.07
    zeh
    0.07
    ä¹Łä¸įä¸Ģå®ļ
    0.07
    åºĶçĶ¨æĬĢæľ¯
    0.07
    ä¹Łä¸į太
    0.07
    Playable
    0.07
    Activations Density 0.119%

    No Known Activations