© 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. 38537
    Prev
    Next
    INDEX
    Explanations

    units following numbers

    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
    fulness
    -0.08
    antry
    -0.08
    affen
    -0.07
    ucha
    -0.07
    enner
    -0.07
    à¹Ģà¸Ľà¸¥
    -0.07
    æĭ¦ä½ı
    -0.07
    borough
    -0.07
    fection
    -0.07
    ewise
    -0.07
    POSITIVE LOGITS
    OUGH
    0.09
    cza
    0.07
    dong
    0.07
    pd
    0.07
    ientos
    0.07
     pháºŃn
    0.07
    àºĩ
    0.07
     Awal
    0.07
    дÑĨа
    0.07
    anded
    0.06
    Activations Density 0.153%

    No Known Activations