© 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. 32637
    Prev
    Next
    INDEX
    Explanations

    file suffixes and abbreviations

    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
    sWith
    -0.12
    ties
    -0.10
    to
    -0.09
    ÑģÑĮ
    -0.09
    ãģ¦ãģĦãĤĭ
    -0.09
    à¥įस
    -0.09
    tools
    -0.09
    types
    -0.08
    ÑĤо
    -0.08
    थ
    -0.08
    POSITIVE LOGITS
    à§įতà§ģ
    0.15
    nyder
    0.14
    ullivan
    0.14
    apphire
    0.13
    cribe
    0.13
    quared
    0.13
    antiago
    0.13
    cribed
    0.13
    ylv
    0.13
    pring
    0.13
    Activations Density 2.573%

    No Known Activations