© 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. 58810
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or entities

    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
    æĻĸ
    -0.09
    çīĻ
    -0.07
    atcher
    -0.07
    å¾Ĺè¿ĩ
    -0.06
    èĬĿ麻
    -0.06
    aux
    -0.06
    itu
    -0.06
    çĵľåŃIJ
    -0.06
    å±±ä¸ĭ
    -0.06
    åĪ°çĿĢ
    -0.06
    POSITIVE LOGITS
    éĩijå®Ŀ
    0.08
    西æĸ¯
    0.08
    /fa
    0.07
    bara
    0.07
    çIJ³
    0.07
    zeÅĽ
    0.07
     sympa
    0.07
     Tulis
    0.07
    reck
    0.07
     Tiết
    0.07
    Activations Density 0.001%

    No Known Activations