© 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. 18452
    Prev
    Next
    INDEX
    Explanations

    normal followed by medical 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
    åĪĩå®ŀå¢ŀ强
    -0.07
    ONGL
    -0.07
    bauer
    -0.07
     ÐŁÐ¾Ð±ÐµÐ´Ñĭ
    -0.07
    ÖĦ
    -0.07
    entina
    -0.07
    HIP
    -0.07
    Dirty
    -0.07
    åľ¨åħ·ä½ĵ
    -0.07
    ILON
    -0.07
    POSITIVE LOGITS
    æŃ£å¸¸çļĦ
    0.14
    normal
    0.12
     normal
    0.12
    -normal
    0.12
     normales
    0.12
    æŃ£å¸¸
    0.12
    erweise
    0.11
     Normal
    0.11
    ä¸įæŃ£å¸¸
    0.11
    Normal
    0.10
    Activations Density 0.072%

    No Known Activations