© 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. 16124
    Prev
    Next
    INDEX
    Explanations

    language, facility, online

    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
    æĥĭ
    -0.06
    ç»ĵç¼ĺ
    -0.06
    QUI
    -0.06
    aviolet
    -0.06
    QUIRE
    -0.06
    áĥ«
    -0.06
    FI
    -0.06
    dept
    -0.06
    æ²¼
    -0.06
    Âł
    -0.06
    POSITIVE LOGITS
    èĻ½çĦ¶ä¸įæĺ¯
    0.11
    indr
    0.09
    buster
    0.09
    ä¸į设
    0.09
    ä¸įæĺ¯ä¸Ģ个
    0.09
    azos
    0.08
    ä¸įåħ¥
    0.08
    .none
    0.08
    edin
    0.08
    æł¹æľ¬ä¸į
    0.08
    Activations Density 0.229%

    No Known Activations