© 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. 34741
    Prev
    Next
    INDEX
    Explanations

    lists of items or structures

    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
    kill
    -0.08
     Tort
    -0.07
    hart
    -0.07
     Zah
    -0.06
    éĿ¢æĿ¡
    -0.06
    ürt
    -0.06
     cele
    -0.06
    Tag
    -0.06
    ód
    -0.06
    xxx
    -0.06
    POSITIVE LOGITS
    èĢĮèµ·
    0.08
    _DROP
    0.08
    æĽ´ç²¾å½©
    0.08
    inqu
    0.07
    _ATOM
    0.07
     Ramb
    0.07
     ByteArray
    0.07
    fal
    0.07
    озна
    0.07
    yip
    0.07
    Activations Density 0.091%

    No Known Activations