© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    medical conditions and specific entities

    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
    ah
    -0.06
    aub
    -0.06
    OfWork
    -0.06
    <|object_ref_start|>
    -0.06
    åĴĮçī¹çĤ¹
    -0.06
    aint
    -0.06
     addObject
    -0.06
    OutOfBounds
    -0.06
    çł¥
    -0.06
    ä¸ĬåĴĮ
    -0.06
    POSITIVE LOGITS
    utherland
    0.09
    cean
    0.08
    hurt
    0.08
    ieras
    0.07
    æĹłäºĭ
    0.07
    coce
    0.07
    nage
    0.07
    inite
    0.07
    iere
    0.07
    маÑĢа
    0.07
    Activations Density 0.366%

    No Known Activations