© 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. 50421
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
    æĿ¿åĴĮ
    -0.06
    boards
    -0.06
    çī¹åĭĴ
    -0.06
    viz
    -0.06
    èįŁèIJĥ
    -0.06
    B
    -0.06
     McCarthy
    -0.06
    ex
    -0.06
    aten
    -0.06
    æĿ¿çļĦ
    -0.06
    POSITIVE LOGITS
    -popup
    0.08
    eih
    0.08
    ython
    0.08
    венÑĮ
    0.08
    ejm
    0.08
    CASCADE
    0.07
    æĸ°åĬłåĿ¡
    0.07
    建设éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    0.07
    <data
    0.07
    دÙĬÙħ
    0.07
    Activations Density 0.005%

    No Known Activations