© 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. 62862
    Prev
    Next
    INDEX
    Explanations

    kinetic and transport processes

    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
    ç»ijæīİ
    -0.07
    ebt
    -0.06
    Serial
    -0.06
     gar
    -0.06
    éĸ£
    -0.06
    ongs
    -0.06
     gare
    -0.06
    ×¢
    -0.06
    楼çļĦ
    -0.06
    æłĪ
    -0.06
    POSITIVE LOGITS
    transport
    0.09
    дÑĢо
    0.09
    particles
    0.09
     poussi
    0.08
     transporting
    0.08
    å¡
    0.08
     PARTIC
    0.08
     Processes
    0.08
    Processes
    0.08
    åľºåĿĩ
    0.08
    Activations Density 0.013%

    No Known Activations