© 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. 14192
    Prev
    Next
    INDEX
    Explanations

    electromechanical systems (MEMS) components

    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
    è¿ľæµģ
    -0.08
    榨
    -0.08
    åĽ´
    -0.07
    egah
    -0.07
    imei
    -0.07
     knit
    -0.07
     запÑĢа
    -0.07
    æĶĺ
    -0.07
    åĩĢæµģåĩº
    -0.07
     framebuffer
    -0.07
    POSITIVE LOGITS
    èģĶåĬ¨
    0.09
    yah
    0.08
    Mounted
    0.08
     mechanism
    0.08
    ÑĪенÑĮ
    0.08
     deflect
    0.08
     lever
    0.08
     swing
    0.08
    带åĬ¨ä¸ĭ
    0.08
    cules
    0.08
    Activations Density 0.134%

    No Known Activations