© 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. 63142
    Prev
    Next
    INDEX
    Explanations

    XML, HTML, and script tags

    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
    Äįina
    -0.06
    ljiv
    -0.06
    ambul
    -0.06
    aba
    -0.06
     Barang
    -0.06
    hoven
    -0.06
     жиз
    -0.06
    onge
    -0.05
    aban
    -0.05
    iin
    -0.05
    POSITIVE LOGITS
    ptos
    0.08
    änder
    0.08
    omp
    0.07
    иÑģÑĤи
    0.07
    dden
    0.07
    æĮĿ
    0.07
    cpy
    0.07
    è¿Ļ两ç§į
    0.07
    å¨Ĩ
    0.07
    à¹Īà¸Ńà¸ĩ
    0.07
    Activations Density 0.017%

    No Known Activations