© 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. 40956
    Prev
    Next
    INDEX
    Explanations

    eosinophil influx

    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
    ved
    -0.09
    INUE
    -0.07
    edly
    -0.07
    è¾Ľäº¥
    -0.07
    nings
    -0.07
    arian
    -0.07
    rove
    -0.07
    ational
    -0.07
    unes
    -0.07
    ëijIJê³ł
    -0.07
    POSITIVE LOGITS
    ়
    0.09
    ivity
    0.08
    çĽĸä¸ĸ
    0.08
    ìį¨
    0.08
    ity
    0.08
    çļĦå°ıæīĭ
    0.08
    -minded
    0.08
    crast
    0.08
    æĢ§å¼º
    0.08
    ikos
    0.08
    Activations Density 0.004%

    No Known Activations