© 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. 24960
    Prev
    Next
    INDEX
    Explanations

    foreign or international contexts

    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
    çĤ³
    -0.09
    åIJij社ä¼ļ
    -0.09
     statewide
    -0.09
    oogle
    -0.08
    社ä¼ļåĬĽéĩı
    -0.07
    åħ¨åŁİ
    -0.07
    ornado
    -0.07
    ä»İ天èĢĮéĻį
    -0.07
     Bates
    -0.07
    наÑģ
    -0.07
    POSITIVE LOGITS
    ä¸İåĽ½åĨħ
    0.11
     foreign
    0.10
    foreign
    0.09
    /global
    0.09
     export
    0.09
    åĴĮåĽ½éĻħ
    0.09
    /dom
    0.09
    çŃīåĽ½éĻħ
    0.09
     Foreign
    0.09
    æݥ轨
    0.08
    Activations Density 0.232%

    No Known Activations