© 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. 51925
    Prev
    Next
    INDEX
    Explanations

    logarithm function

    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
    顾åIJįæĢĿ
    -0.08
    å±±éķĩ
    -0.08
    ä¹į
    -0.08
    sak
    -0.07
    ↵			↵
    -0.07
    ãģ£ãģ¨
    -0.07
    oling
    -0.07
    ésre
    -0.07
    onger
    -0.07
    ENCED
    -0.07
    POSITIVE LOGITS
    åĴĮè°ĥæķ´
    0.06
    antee
    0.06
    èĥ½æīĭ
    0.06
     beloved
    0.06
    Untitled
    0.06
    izard
    0.06
     orto
    0.06
    λÏİν
    0.06
    æĭ¾
    0.06
     ÙĦØ°
    0.06
    Activations Density 0.003%

    No Known Activations