© 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. 28717
    Prev
    Next
    INDEX
    Explanations

    diplomatic roles and titles

    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
    æĺ¯éĽĨ
    -0.09
    .measure
    -0.07
    æѦèѦ
    -0.07
    社ä¼ļåħ¬ä¼Ĺ
    -0.07
     Highland
    -0.07
    çIJĨäºĭéķ¿
    -0.07
    äºĶèĬ±
    -0.07
    åĮĹåĮº
    -0.07
    andbox
    -0.07
    psc
    -0.07
    POSITIVE LOGITS
     diplomatic
    0.16
    å¤ĸ交
    0.15
     diplomacy
    0.13
     diplomat
    0.13
     diplomats
    0.12
     diplom
    0.12
     embassy
    0.11
     envo
    0.11
     Dipl
    0.11
     exchange
    0.10
    Activations Density 0.202%

    No Known Activations