© 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. 30477
    Prev
    Next
    INDEX
    Explanations

    back to the Power Supply

    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
    yte
    -0.07
    stream
    -0.07
    orma
    -0.06
    yson
    -0.06
     stream
    -0.06
    STREAM
    -0.06
     exc
    -0.06
    escal
    -0.06
    åIJī祥å¦ĤæĦı
    -0.06
    Slides
    -0.06
    POSITIVE LOGITS
    ipo
    0.08
    kola
    0.08
    å½¢æĪIJä¸Ģ个
    0.07
    èĢĮä¸įè§ģ
    0.07
    angler
    0.07
    aises
    0.07
    igator
    0.07
    clus
    0.07
    iaux
    0.07
    æł¼å¤ĸçļĦ
    0.06
    Activations Density 0.004%

    No Known Activations