© 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. 3531
    Prev
    Next
    INDEX
    Explanations

    integrate, morphology, ofs

    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
    iler
    -0.08
    åħ¬å®³
    -0.07
    _kind
    -0.07
    çľĭåľ¨çľ¼éĩĮ
    -0.07
    azah
    -0.07
     Sez
    -0.07
    rob
    -0.07
    佬
    -0.07
     Ùħعد
    -0.07
    ftype
    -0.06
    POSITIVE LOGITS
    ÙĪÙĬات
    0.08
    æļ¦
    0.07
    åįģéĩĮ
    0.07
    andon
    0.07
    åĽŀæĿ¥çļĦ
    0.07
     Norris
    0.07
    åĽŀæĿ¥
    0.07
    è¯ķè¡Į
    0.07
    atron
    0.07
    itol
    0.07
    Activations Density 0.001%

    No Known Activations