© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    has/have/contains things

    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
    åħ¨ä¼ļ
    -0.07
     bufsize
    -0.07
    Ú¯ÙĪÙĨ
    -0.07
    æľīåķ¥
    -0.06
    çļĦèĥĮåIJİ
    -0.06
    ope
    -0.06
    èµ°ä¸ĭåİ»
    -0.06
    ibar
    -0.06
    缸åħ³æĸĩ件
    -0.06
     feh
    -0.06
    POSITIVE LOGITS
     помимо
    0.10
    à¸Ńะà¹Ħรà¸ļà¹īาà¸ĩ
    0.10
     ë¶Ħëªħ
    0.08
     sowohl
    0.08
    ä¸įæŃ¢
    0.08
     både
    0.08
    åħ©ç¨®
    0.08
     certes
    0.08
    两类
    0.08
    两ç§į
    0.08
    Activations Density 0.157%

    No Known Activations