© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2298
    Prev
    Next
    INDEX
    Explanations

    Andreas names, Duan names

    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
    deaux
    -0.13
    ibrator
    -0.10
    meÄiju
    -0.10
    olland
    -0.09
    croft
    -0.09
    erber
    -0.09
    egner
    -0.09
    intang
    -0.09
    дей
    -0.09
    öld
    -0.09
    POSITIVE LOGITS
    oriously
    0.09
    emon
    0.08
    ly
    0.08
    ../../../
    0.08
    -lived
    0.07
    ness
    0.07
    ynam
    0.07
    uring
    0.07
    Ĺ
    0.07
    orf
    0.07
    Activations Density 0.002%

    No Known Activations