© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    integer bit sizes

    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
    ushima
    -0.08
    pared
    -0.08
    checkout
    -0.07
    Checkout
    -0.07
    breadcrumb
    -0.07
    optgroup
    -0.07
     checkout
    -0.07
    ÑĢоли
    -0.07
    çĬ¯
    -0.07
     STDERR
    -0.07
    POSITIVE LOGITS
    åĽĽä¸ª
    0.07
    åĽĽä½į
    0.07
    åĽĽåįĥ
    0.07
    åºĦ
    0.07
     htonl
    0.07
    ÃŃž
    0.07
    å¸Īå¼Ł
    0.07
     native
    0.07
    hton
    0.07
    æIJº
    0.06
    Activations Density 0.106%

    No Known Activations