© 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. 9153
    Prev
    Next
    INDEX
    Explanations

    from due by

    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
    iscard
    -0.07
    grass
    -0.06
    ieten
    -0.06
    erten
    -0.06
    æīĢéľĢè¦ģçļĦ
    -0.06
    Õ¥Õ½
    -0.06
    chia
    -0.06
    èĩªæ²»
    -0.06
    angered
    -0.06
    é©ĹèŃī
    -0.06
    POSITIVE LOGITS
    两åѦä¸Ģåģļ
    0.09
    两个æĸ¹éĿ¢
    0.08
     ÑģобÑģÑĤвенно
    0.08
    illion
    0.08
    æĬĢæľ¯è¿ĽæŃ¥
    0.08
    åIJĦç§įåİŁåĽł
    0.08
    ç§ijæĬĢè¿ĽæŃ¥
    0.07
    æ¼ı
    0.07
    æĹłç©·çļĦ
    0.07
    æѤäºĭ
    0.07
    Activations Density 0.168%

    No Known Activations