© 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. 20282
    Prev
    Next
    INDEX
    Explanations

    clinical 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
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.09
    ×Ĺ×Ļ
    -0.09
    ignum
    -0.09
     пони
    -0.09
    èĻ«å®³
    -0.08
     temb
    -0.08
    dden
    -0.08
    èĩªçĦ¶ä¿ĿæĬ¤åĮº
    -0.08
    éħ¥
    -0.08
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    -0.08
    POSITIVE LOGITS
     clinical
    0.13
     Clinical
    0.12
    Clinical
    0.11
    临åºĬ
    0.10
     clinically
    0.10
    clinical
    0.10
     clinicians
    0.10
     patients
    0.10
    çļĦ临åºĬ
    0.10
     bedside
    0.09
    Activations Density 2.792%

    No Known Activations