© 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. 44854
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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
    缺
    -0.07
    åŃĺåľ¨çļĦ
    -0.07
    aze
    -0.07
    enhagen
    -0.07
    æ´»
    -0.06
    èģĺ
    -0.06
    åѤ
    -0.06
    ç³»
    -0.06
    çĦ°
    -0.06
    enge
    -0.06
    POSITIVE LOGITS
     randomness
    0.13
     random
    0.11
    random
    0.11
    éļıæľº
    0.11
    /random
    0.11
    -random
    0.11
     Random
    0.10
    RANDOM
    0.10
    Random
    0.09
    .random
    0.09
    Activations Density 0.018%

    No Known Activations