© 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. 34207
    Prev
    Next
    INDEX
    Explanations

    Calendar, download, code annotations

    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
    -0.09
    elik
    -0.06
    æĭ©
    -0.06
    辨
    -0.06
    rowse
    -0.06
    utama
    -0.06
    ảnh
    -0.06
    èį£èªīæĦŁ
    -0.06
    论è¯ģ
    -0.06
    rou
    -0.06
    POSITIVE LOGITS
    FFE
    0.08
    ç«¥åŃIJ
    0.08
    èµ·è¯ī书
    0.08
    еÑģÑĤи
    0.07
    éĻ
    0.07
    HeaderText
    0.07
    åĪĪ
    0.07
    `\
    0.07
    (fig
    0.07
    .defaults
    0.07
    Activations Density 0.002%

    No Known Activations