© 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. 62472
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    olino
    -0.10
    两ä¸į误
    -0.08
    缸åħ³æݨèįIJ
    -0.07
    åĽ¢çļĦ
    -0.07
    液çļĦ
    -0.06
    åľĺ
    -0.06
    eton
    -0.06
    ä½ľä¸ºåĽ½åĨħ
    -0.06
    åİ¿å§Ķåī¯ä¹¦è®°
    -0.06
    еÑīа
    -0.06
    POSITIVE LOGITS
    ä¸įåħ¨
    0.08
    poon
    0.07
    leased
    0.07
    ĸ
    0.07
    imana
    0.07
    åı¯ä¸º
    0.07
     ÙħÙħ
    0.07
    cky
    0.07
    è³
    0.07
    ycz
    0.07
    Activations Density 0.005%

    No Known Activations