© 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. 40992
    Prev
    Next
    INDEX
    Explanations

    purpose, vision, mission, goals

    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
    habil
    -0.08
    avr
    -0.08
    æľī礼
    -0.08
    潺
    -0.08
    çļĦæĬĢå·§
    -0.07
    ãĥªãĤ¨
    -0.07
    æĬĢå·§
    -0.07
    ÃŃÅ¡
    -0.07
    .urlopen
    -0.07
    ç»ĵå®ŀ
    -0.07
    POSITIVE LOGITS
    缮æłĩåĴĮ
    0.12
    æĸ¹åIJij
    0.11
     goals
    0.11
     direction
    0.11
    缮æłĩ
    0.11
    æĺİç¡®çļĦ
    0.10
    æĦ¿æĻ¯
    0.10
    å¥ĭæĸĹ缮æłĩ
    0.10
     overarching
    0.10
    æĸ¹åIJijåĴĮ
    0.10
    Activations Density 0.085%

    No Known Activations