© 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. 15784
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations, prefixes, and terms

    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
     ↵
    -0.07
    obe
    -0.07
    erno
    -0.06
    èĺ
    -0.06
    aster
    -0.06
    æ
    -0.06
    æĬľãģij
    -0.06
      ↵
    -0.06
    Ö·
    -0.06
    æĭįäºĨæĭį
    -0.06
    POSITIVE LOGITS
    .Expect
    0.08
    irim
    0.08
    éķ¿èĻ¹
    0.08
     gaussian
    0.07
     fras
    0.07
    .Euler
    0.07
    ÑģлÑĮ
    0.07
    .Marker
    0.07
    Ĵ
    0.07
    Gam
    0.07
    Activations Density 0.061%

    No Known Activations