© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16843
    Prev
    Next
    INDEX
    Explanations

    globalization and internationalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽ½æľīèµĦ产
    -0.22
    æī§
    -0.22
    åĺī宾
    -0.21
    ä¸įåĩºæĿ¥
    -0.21
    è´¨
    -0.20
    夺
    -0.20
    åľ¨çİ°åľº
    -0.20
    etag
    -0.20
    åľ¨åŃ¦æł¡
    -0.19
    累计
    -0.19
    POSITIVE LOGITS
    åħ¨çIJĥåĮĸ
    0.32
    -global
    0.30
     global
    0.29
    åħ¨çIJĥç»ıæµİ
    0.29
    åħ¨çIJĥ
    0.28
    /global
    0.28
    ä¸ĸçķĮ
    0.28
    (global
    0.27
     world
    0.25
    ä¸ĸçķĮçļĦ
    0.25
    Activations Density 0.020%

    No Known Activations