© 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. 39166
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and names

    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
    berger
    -0.08
    éĹ´æŃĩ
    -0.07
    icle
    -0.06
    è°ĥåĪ°
    -0.06
    ä¸įéĹ´æĸŃ
    -0.06
    λεγ
    -0.06
    贯穿äºİ
    -0.06
    ä½İåIJ¸
    -0.06
    perial
    -0.06
    Ö
    -0.06
    POSITIVE LOGITS
    说æĸĩ
    0.09
    CreateInfo
    0.08
    ç»Ħè¯į
    0.08
    رÙħ
    0.08
    åŃĹçļĦ
    0.08
    åįģä¹Ŀ
    0.07
    æĭĨå¼Ģ
    0.07
    ูà¸ģ
    0.07
    æ±Łå¤ı
    0.07
    òng
    0.07
    Activations Density 0.004%

    No Known Activations