© 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. 62809
    Prev
    Next
    INDEX
    Explanations

    for each

    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
    eka
    -0.07
    arella
    -0.07
    对ä¸ĢäºĽ
    -0.07
     ضÙħ
    -0.07
    ebro
    -0.07
    ellit
    -0.06
    è¿Ļåľ¨
    -0.06
    pak
    -0.06
     rowspan
    -0.06
    ÄĻb
    -0.06
    POSITIVE LOGITS
     each
    0.18
    æ¯ı个
    0.17
     Each
    0.15
     chaque
    0.15
    each
    0.15
    Each
    0.15
     cada
    0.14
    à¹ģà¸ķà¹Īละ
    0.14
    æ¯ıåĢĭ
    0.14
     каждой
    0.14
    Activations Density 0.029%

    No Known Activations