© 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. 9793
    Prev
    Next
    INDEX
    Explanations

    statistical probability randomness

    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
    berman
    -0.09
    æĶ¹åĬ¨
    -0.08
     обой
    -0.07
    _extent
    -0.07
    ypass
    -0.07
    ä¸īèĢħ
    -0.07
    åĬłå·¥å·¥èīº
    -0.07
    ogan
    -0.07
    è·Ĩ
    -0.07
    交æīĢ
    -0.07
    POSITIVE LOGITS
    éļıæľº
    0.13
     statistically
    0.13
     probabil
    0.13
    ç»Łè®¡åѦ
    0.13
     random
    0.12
    ç»Łè®¡
    0.12
     statistical
    0.12
     statist
    0.12
    æ¦Ĥçİĩ
    0.12
     randomness
    0.12
    Activations Density 0.014%

    No Known Activations