© 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. 48425
    Prev
    Next
    INDEX
    Explanations

    network interface card or port

    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
    éļ¾æ±Ĥ
    -0.08
     density
    -0.07
    OPS
    -0.07
    beck
    -0.07
    æ»ŀåľ¨
    -0.07
    cius
    -0.07
    ä¸įæķ£
    -0.07
     lapse
    -0.07
    /exec
    -0.07
    ä¸į缺
    -0.07
    POSITIVE LOGITS
    åı£çļĦ
    0.08
    lisi
    0.08
    缴éĢļ
    0.07
    åĪ®
    0.07
     Dedicated
    0.07
    ä¸Ĭ好
    0.07
    INAN
    0.07
     Ports
    0.07
     Mounted
    0.07
     artery
    0.07
    Activations Density 0.080%

    No Known Activations