© 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. 23701
    Prev
    Next
    INDEX
    Explanations

    dating website

    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
    ány
    -0.09
    ä¹ŁåºĶ该
    -0.07
    _stub
    -0.07
    nac
    -0.07
    æīĢæıIJä¾ĽçļĦ
    -0.07
    ady
    -0.07
    enden
    -0.07
    ãs
    -0.07
    uhan
    -0.07
    วัà¸Ĵà¸Ļà¹Į
    -0.07
    POSITIVE LOGITS
    âĸ²
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    ritel
    0.07
    âĸ·
    0.07
    æĮĩ
    0.06
    èĪľ
    0.06
    itia
    0.06
    plies
    0.06
    åĻ¨
    0.06
    svg
    0.06
    Activations Density 0.001%

    No Known Activations