© 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. 15688
    Prev
    Next
    INDEX
    Explanations

    nested list or array properties

    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
    º
    -0.07
    æĦıä¹īçļĦ
    -0.06
    æģ¤
    -0.06
    ároz
    -0.06
    æĺ¯éĿŀ
    -0.06
    ç¯Ĩ
    -0.06
    ä¸Ģä¸Ģ
    -0.06
    ather
    -0.06
     Kash
    -0.06
    æĸ¹åIJij
    -0.06
    POSITIVE LOGITS
    æ¼¾
    0.09
    详ç»Ĩæııè¿°
    0.09
     terdiri
    0.08
    è¿ŀæİ¥æľī
    0.08
    为åIJĮåѦ们
    0.08
    èݱåĿŀ
    0.08
    详ç»ĨäºĨ解
    0.08
    ÑģÑĤÑĢебо
    0.08
    åıĬåĪ©æģ¯
    0.08
     nested
    0.08
    Activations Density 0.029%

    No Known Activations