© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10587
    Prev
    Next
    INDEX
    Explanations

    mathematical variable definitions

    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
    çIJ¦
    -0.07
    èĢĮæĪIJ
    -0.07
    ault
    -0.06
    æĹłéĻIJçļĦ
    -0.06
    kel
    -0.06
    iaux
    -0.06
    .offsetHeight
    -0.06
    çºł
    -0.06
    éĹ»
    -0.06
    ä¾Ľç»Ļ
    -0.06
    POSITIVE LOGITS
    ascript
    0.09
    deka
    0.07
     ÐĴÑģем
    0.07
    åѦéĩij
    0.07
    为顾客
    0.07
    ä¸Ĭè¡Į
    0.07
    isca
    0.07
    éĢīæĭ©éĢĤåIJĪèĩªå·±çļĦ
    0.07
     вм
    0.07
    ó
    0.07
    Activations Density 0.013%

    No Known Activations