© 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. 16244
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
    ÑģÑĮ
    -0.09
    esten
    -0.09
    ogan
    -0.07
    ÙIJÙĬÙıÙij
    -0.07
    اÙĥ
    -0.07
    erma
    -0.07
    uelas
    -0.07
    计çļĦ
    -0.07
    edis
    -0.07
    itan
    -0.07
    POSITIVE LOGITS
    ÛĮ
    0.11
    gadas
    0.09
    gada
    0.09
    gado
    0.09
    ories
    0.08
    nya
    0.08
     selben
    0.08
    odable
    0.08
    artige
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    Activations Density 0.059%

    No Known Activations