© 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. 31783
    Prev
    Next
    INDEX
    Explanations

    patients with medical 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
    awn
    -0.08
    ordinates
    -0.08
    ness
    -0.08
    NESS
    -0.08
    ancers
    -0.07
    ordinate
    -0.07
    gers
    -0.07
    ¾
    -0.07
    orld
    -0.07
    ÅĽci
    -0.07
    POSITIVE LOGITS
    /client
    0.09
    stwo
    0.08
    èle
    0.08
    antry
    0.08
    acle
    0.08
    elor
    0.08
    staking
    0.08
    oudre
    0.08
    ricia
    0.07
    ecchio
    0.07
    Activations Density 0.108%

    No Known Activations