© 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. 58240
    Prev
    Next
    INDEX
    Explanations

    decimal numbers and calculations

    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
    满å¿ĥ
    -0.07
    ÑĬÑĢжа
    -0.07
    èĭ¥ä¸į
    -0.07
    efeller
    -0.07
    æľīåħ³è´Łè´£äºº
    -0.07
     unsus
    -0.06
    ì»·
    -0.06
    atever
    -0.06
    为å¸Ī
    -0.06
    馨
    -0.06
    POSITIVE LOGITS
    ért
    0.08
    åģļåĪ°
    0.07
    _basename
    0.07
    é§ķ
    0.07
    sf
    0.07
    翼翼
    0.07
    _:
    0.07
    ezer
    0.07
    è´¨çļĦ
    0.07
    GX
    0.07
    Activations Density 0.007%

    No Known Activations