© 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. 60256
    Prev
    Next
    INDEX
    Explanations

    time flown 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
    æľĢé«ĺåı¯
    -0.08
    agli
    -0.08
    æĸ¹åľĨ
    -0.07
    åĦ¿åª³
    -0.07
    éĽªä¸Ń
    -0.07
    绾ç»İ
    -0.07
    åħ«æĪIJ
    -0.07
    ä¸Ģ鸣
    -0.07
    ä¸ĢæĿ¡é¾Ļ
    -0.07
    åĪĿ次
    -0.07
    POSITIVE LOGITS
    æµģéĢĿ
    0.14
    éĢĿåİ»
    0.13
     elapsed
    0.11
    åħīéĺ´
    0.11
    èĭį
    0.10
     trôi
    0.10
    elapsed
    0.10
    éĢĿ
    0.10
    æݨ移
    0.10
    é£ŀéĢĿ
    0.10
    Activations Density 0.126%

    No Known Activations