© 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. 13908
    Prev
    Next
    INDEX
    Explanations

    memory lane

    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
    åĬłæĭ¿å¤§çļĦ
    -0.08
    çĤ¹åĩ»éĺħ读åİŁæĸĩ
    -0.08
    å¿Ĺæĺİ
    -0.08
    RootElement
    -0.07
    ç«ĭæ¡Īä¿¡æģ¯
    -0.07
    itionally
    -0.07
    ÙĨع
    -0.07
    enam
    -0.07
    ằn
    -0.07
    åħ¢åħ¢ä¸ļä¸ļ
    -0.07
    POSITIVE LOGITS
     olev
    0.06
    åĽ½èIJ¥
    0.06
    wai
    0.06
    ç£ĭ
    0.06
    hole
    0.06
    éĩĮçļĦ
    0.06
    èĦijæµ·
    0.06
    ephy
    0.06
    æIJľç´¢
    0.06
    اÙģÙĦ
    0.06
    Activations Density 0.001%

    No Known Activations