© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32130
    Prev
    Next
    INDEX
    Explanations

    network cables and transmission media

    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
    çĮ®
    -0.08
    bris
    -0.08
    çļĦ太éĺ³
    -0.07
    æ©ŁåĻ¨äºº
    -0.07
    å·§
    -0.07
     GLuint
    -0.06
    IEWS
    -0.06
    èIJ½èIJ½
    -0.06
    溶
    -0.06
    à¹ģหล
    -0.06
    POSITIVE LOGITS
     cable
    0.11
    ä¼łè¾ĵ
    0.10
    çĶµç¼Ĩ
    0.10
     Cable
    0.10
     cables
    0.10
     transmitting
    0.09
     kabel
    0.09
     кабелÑĮ
    0.09
     Ethernet
    0.09
     transmission
    0.09
    Activations Density 0.059%

    No Known Activations