© 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. 14898
    Prev
    Next
    INDEX
    Explanations

    foreign investment and markets

    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
    人人
    -0.08
     everyone
    -0.07
     Everyone
    -0.06
    åĴĮ大家åĪĨ享
    -0.06
    æ·ij女
    -0.06
     society
    -0.06
    éĤª
    -0.06
    人人éĥ½
    -0.06
    åĴĮ大家
    -0.06
    æĬĬæīĢæľī
    -0.06
    POSITIVE LOGITS
     abroad
    0.14
    è·¨å¢ĥ
    0.14
    è·¨åĽ½
    0.13
     overseas
    0.13
     foreign
    0.12
    ä¸¤åĽ½
    0.12
    æľ¬åĽ½
    0.12
    foreign
    0.11
     Foreign
    0.11
    å¢ĥå¤ĸ
    0.11
    Activations Density 0.180%

    No Known Activations