© 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. 33341
    Prev
    Next
    INDEX
    Explanations

    arrays or lists

    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
    а
    -0.12
    ness
    -0.10
    ап
    -0.09
    ação
    -0.09
    szy
    -0.08
    nement
    -0.08
    iveness
    -0.08
    ipping
    -0.08
    lide
    -0.08
    room
    -0.08
    POSITIVE LOGITS
    Ùĩ
    0.17
    ä½Ĩä¸įéĻIJäºİ
    0.15
    人
    0.12
    ëį°
    0.11
    åħ¨å¿ĥåħ¨æĦı
    0.11
    as
    0.11
    ãģĬãģĿãĤīãģı
    0.11
    es
    0.10
    ä¼ĹæīĢåij¨çŁ¥
    0.10
    u
    0.10
    Activations Density 0.128%

    No Known Activations