© 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. 17937
    Prev
    Next
    INDEX
    Explanations

    media analysis and discussion

    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
    shire
    -0.10
    /browse
    -0.09
    itude
    -0.09
    goed
    -0.09
    ÑĤаки
    -0.08
    ENCY
    -0.08
    itudes
    -0.08
    heit
    -0.07
    umer
    -0.07
    ÑİÑĤ
    -0.07
    POSITIVE LOGITS
    onald
    0.09
    hape
    0.09
    wipe
    0.08
     tảng
    0.08
    aybe
    0.08
    มวลà¸Ĭà¸Ļ
    0.08
     savvy
    0.08
    urgical
    0.08
    hav
    0.08
     spoÅĤecznoÅĽci
    0.08
    Activations Density 0.055%

    No Known Activations