© 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. 50379
    Prev
    Next
    INDEX
    Explanations

    biological and 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
    abah
    -0.07
    olec
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
    гни
    -0.07
    tright
    -0.06
    roll
    -0.06
    UniqueId
    -0.06
    buch
    -0.06
    ounder
    -0.06
    ัà¸ĩà¸ģ
    -0.06
    POSITIVE LOGITS
    ãĤĴæĦıèŃĺ
    0.07
    esimo
    0.07
    åģļè´¡çĮ®
    0.07
    çłĶ究æĪIJæŀľ
    0.06
    chon
    0.06
     noqa
    0.06
    beg
    0.06
    ä¸ĢäºĮ
    0.06
    áºŃp
    0.06
    aro
    0.06
    Activations Density 0.059%

    No Known Activations