© 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. 21066
    Prev
    Next
    INDEX
    Explanations

    pathophysiology and pathogenesis

    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
    orary
    -0.08
    žil
    -0.07
    abis
    -0.07
    åħ¶çĥ¦
    -0.07
    edImage
    -0.07
    outine
    -0.07
    ness
    -0.07
    lah
    -0.07
    ç²¾èī¯
    -0.07
    tsel
    -0.07
    POSITIVE LOGITS
    å±ĤéĿ¢çļĦ
    0.08
    aub
    0.07
    大æĦı
    0.07
     underlying
    0.07
    ä½ķåľ¨
    0.07
     پرد
    0.07
    å±ĤéĿ¢
    0.07
    éĥģ
    0.07
    añ
    0.07
    éĢı
    0.06
    Activations Density 0.014%

    No Known Activations