© 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. 18644
    Prev
    Next
    INDEX
    Explanations

    cancer, diseases, and medical body parts

    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
    arser
    -0.07
    olutely
    -0.07
    æĦŁåįģ足
    -0.07
    ÄĽjÅ¡ÃŃ
    -0.07
    壮大
    -0.07
    ìłģìĿ´ê³ł
    -0.06
    ãĤĩãģĨ
    -0.06
    ologically
    -0.06
     <![
    -0.06
    ipe
    -0.06
    POSITIVE LOGITS
    ographique
    0.10
    ÙĪبر
    0.07
    hada
    0.07
    ìĶ¨
    0.07
    atique
    0.07
    ográfico
    0.07
    iants
    0.06
    _executor
    0.06
    ologique
    0.06
    ancar
    0.06
    Activations Density 0.789%

    No Known Activations