© 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. 31388
    Prev
    Next
    INDEX
    Explanations

    package management

    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
    anou
    -0.08
    .generated
    -0.08
    utherland
    -0.07
    ä¸įè¿ĩæĿ¥
    -0.07
    è¿İ宾
    -0.07
    agenda
    -0.07
    ipan
    -0.07
    ollen
    -0.07
    çĹ´
    -0.07
    å¤įä½į
    -0.07
    POSITIVE LOGITS
     packaging
    0.09
     catalog
    0.09
    .pkg
    0.08
     depot
    0.08
    _INSTALL
    0.08
    /install
    0.07
    ä¿¡èªī
    0.07
     Packaging
    0.07
     Catalog
    0.07
    istar
    0.07
    Activations Density 0.561%

    No Known Activations