© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25167
    Prev
    Next
    INDEX
    Explanations

    randomness and testing

    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
    纺
    -0.07
    大åħ¸
    -0.07
    à¸ªà¸±à¸Ľà¸Ķาหà¹Į
    -0.07
    ĵĺ
    -0.07
    éĶ¦æłĩ
    -0.07
    åĿIJèIJ½åľ¨
    -0.07
    èµĦ
    -0.06
    ulf
    -0.06
    çĿĢåij¢
    -0.06
    å±Ĭ
    -0.06
    POSITIVE LOGITS
     randomly
    0.14
    éļıæľº
    0.14
     random
    0.12
    éļ¨æ©Ł
    0.12
     Random
    0.11
     getRandom
    0.11
    random
    0.11
     randomized
    0.11
    Random
    0.10
    æµĭè¯ķ
    0.09
    Activations Density 0.031%

    No Known Activations