© 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. 42366
    Prev
    Next
    INDEX
    Explanations

    sorting lists by order

    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
    ÙĪرÛĮ
    -0.08
     rp
    -0.08
    å¦ĥ
    -0.08
     McMaster
    -0.07
    onyme
    -0.07
    AHAN
    -0.07
    _processors
    -0.07
    chine
    -0.07
    rypton
    -0.07
    NÄIJ
    -0.07
    POSITIVE LOGITS
     order
    0.08
    _order
    0.08
    ¬ģ
    0.08
     orders
    0.07
    Order
    0.07
     orden
    0.07
    çļĦ顺åºı
    0.07
    à¸Īัà¸Ķ
    0.07
    顺åºı
    0.07
    λÏİ
    0.07
    Activations Density 0.106%

    No Known Activations