© 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. 44070
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands

    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
    Ùĭ
    -0.06
    enj
    -0.06
    izz
    -0.06
    éĢ¢
    -0.06
    ingkan
    -0.06
    ìĿį
    -0.06
    ing
    -0.06
    a
    -0.06
    ÑģÑĮ
    -0.05
    enha
    -0.05
    POSITIVE LOGITS
    дав
    0.08
    olation
    0.08
    roat
    0.08
    ceb
    0.08
    (#)
    0.08
    лда
    0.08
    вода
    0.08
    ittest
    0.08
    âĢ¦ãĢĤ
    0.08
    вого
    0.07
    Activations Density 0.002%

    No Known Activations