© 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. 20042
    Prev
    Next
    INDEX
    Explanations

    diabetes mellitus

    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
    åĪ©çī©
    -0.08
    DOCKER
    -0.07
    LENGTH
    -0.07
    <|box_end|>
    -0.07
    è´Ŀ壳
    -0.07
    /docker
    -0.07
    èļĮ
    -0.07
    /ajax
    -0.07
    åį·åħ¥
    -0.07
     lineback
    -0.07
    POSITIVE LOGITS
    ç³ĸå°¿çĹħ
    0.17
     diabetes
    0.17
     Diabetes
    0.16
    è¡Ģç³ĸ
    0.16
     insulin
    0.15
     diabetic
    0.15
     glucose
    0.14
    ç³ĸå°¿çĹħæĤ£èĢħ
    0.14
    èĥ°å²Ľç´ł
    0.13
    èĥ°å²Ľ
    0.12
    Activations Density 0.270%

    No Known Activations