© 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. 51370
    Prev
    Next
    INDEX
    Explanations

    floor or second

    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
    rut
    -0.09
    ismet
    -0.07
    uem
    -0.07
    tar
    -0.07
    rin
    -0.07
    .setScale
    -0.07
    ÙģÙĬر
    -0.07
    uah
    -0.06
    åĮħçļ®
    -0.06
    ãģ®éģķãģĦ
    -0.06
    POSITIVE LOGITS
    inos
    0.09
     bersangkutan
    0.07
    aska
    0.07
    ilda
    0.07
    åĩºéĿ¢
    0.07
    à¸ķรี
    0.07
    avan
    0.07
    anches
    0.07
    inda
    0.07
    æĬ¬
    0.07
    Activations Density 0.002%

    No Known Activations