© 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. 28352
    Prev
    Next
    INDEX
    Explanations

    disease and its conditions

    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
    ä¹ĭéģ¥
    -0.09
    à¦ķার
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    åĽŀäºĭ
    -0.08
    管æīĢ
    -0.08
    IMUM
    -0.08
    abay
    -0.08
    apor
    -0.08
     nhiên
    -0.08
    uyan
    -0.08
    POSITIVE LOGITS
    cape
    0.09
     ridden
    0.09
    fully
    0.09
    ridden
    0.08
    ownt
    0.07
     táºŃt
    0.07
    liness
    0.07
    hood
    0.07
    ca
    0.07
    orous
    0.07
    Activations Density 0.114%

    No Known Activations