© 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. 65524
    Prev
    Next
    INDEX
    Explanations

    mathematical limits and equations

    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
    ĥĿ
    -0.08
    pecified
    -0.07
     marka
    -0.06
    æīĵä¸Ĭ
    -0.06
    fulness
    -0.06
    åı¯ä¸į
    -0.06
    .cs
    -0.06
     vek
    -0.06
    å¦Ĥä½ķåºĶ对
    -0.06
    åºĶæĺ¯
    -0.06
    POSITIVE LOGITS
    OVO
    0.08
    aix
    0.08
     Erm
    0.08
    ä¹ĭéĹ´æľī
    0.08
    olan
    0.07
    allen
    0.07
    iono
    0.07
     erm
    0.07
    гаÑĢ
    0.07
    kland
    0.07
    Activations Density 0.054%

    No Known Activations