© 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. 11719
    Prev
    Next
    INDEX
    Explanations

    national origins and conflicts

    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
    ä¸İä¼Ĺ
    -0.23
    ä¸įæľį
    -0.21
    éķĹ
    -0.20
    å¾Ĺ罪
    -0.19
    ä¸İä¼Ĺä¸įåIJĮ
    -0.19
    èĨĽ
    -0.19
     lobbyist
    -0.19
    æĭ¿åĩºæĿ¥
    -0.19
    èł¢
    -0.18
    .asp
    -0.18
    POSITIVE LOGITS
    æ³®
    0.22
    åľ¨è¿ĩ渡
    0.22
    å·¥ä½ľç»Ħ
    0.21
    人åijĺ
    0.21
    éĺŁåijĺ
    0.20
    zte
    0.20
    Ùģت
    0.20
    åľ¨è¿ĩæ¸¡æľŁ
    0.19
    å½ĵåľ°
    0.19
    å½ĵå±Ģ
    0.19
    Activations Density 0.053%

    No Known Activations