© 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. 28637
    Prev
    Next
    INDEX
    Explanations

    position and location

    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
    ippers
    -0.09
    usche
    -0.07
    ä¸įä¼ij
    -0.07
    GetCurrent
    -0.07
    aald
    -0.07
    itul
    -0.07
    katan
    -0.07
     Vergangen
    -0.07
    antry
    -0.07
    versions
    -0.07
    POSITIVE LOGITS
    ä½įç½®
    0.18
    ä½įç½®ä¸Ĭ
    0.15
    çļĦä½įç½®
    0.15
    ä½įç½®çļĦ
    0.15
    ä½įç½®åĴĮ
    0.14
     position
    0.14
     location
    0.13
     positions
    0.12
     ÑĢаÑģположениÑı
    0.12
     ìľĦì¹ĺ
    0.12
    Activations Density 0.172%

    No Known Activations