© 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. 13365
    Prev
    Next
    INDEX
    Explanations

    code or programming constructs

    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
    è¿Ļ件äºĭæĥħ
    -0.27
    æĪĸèĢħæĺ¯
    -0.26
    æīįèĥ½å¤Ł
    -0.25
    ä½Ĩæĺ¯åľ¨
    -0.23
    å¾Īæľīåı¯èĥ½
    -0.23
    åĵªä¸Ģ个
    -0.23
    ä¸ŃåĽ½æĶ¿åºľ
    -0.23
    çľĭä¸Ģçľĭ
    -0.23
    ç§ijåѦæĬĢæľ¯
    -0.22
    没æľīåĬŀæ³ķ
    -0.22
    POSITIVE LOGITS
    åĽ½ä¼ģ
    0.28
    ìĹĶ
    0.26
    æ°ijä¼ģ
    0.26
    ãģ£ãģ¦ãĤĭ
    0.25
     info
    0.24
    ç½ij讯
    0.24
    ãģĹãģ¦ãĤĭ
    0.23
    为åķ¥
    0.22
    没åķ¥
    0.22
     Dept
    0.20
    Activations Density 1.330%

    No Known Activations