© 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. 16824
    Prev
    Next
    INDEX
    Explanations

    Japanese/Chinese text structures

    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
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.22
    çŁ¥
    -0.21
    ÑĩÑĢежден
    -0.21
    åŀº
    -0.21
    宣
    -0.21
     ÐIJлекÑģан
    -0.21
    æİĴ
    -0.20
     ÐŁÐ¾Ñĩем
    -0.20
    åĪĹ
    -0.20
    åħµ
    -0.20
    POSITIVE LOGITS
    æĢ»è§īå¾Ĺ
    0.22
    㶲
    0.20
    游æĪı代
    0.20
    骥
    0.19
    ßķ
    0.19
    æľĥåĵ¡è¨»åĨĬ
    0.19
    ä¸ŃåĽ½ç½ij游
    0.19
    游æĪıè£ħå¤ĩ
    0.18
    ä¿Ĺè¯Ŀ说
    0.18
    è§īå¾Ĺèĩªå·±
    0.18
    Activations Density 0.010%

    No Known Activations