© 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. 16239
    Prev
    Next
    INDEX
    Explanations

    detecting "user" or "them" followed by "to"

    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
    æĪij说
    -0.22
    çŃīçĿĢ
    -0.20
    å¾ĹçĽĬäºİ
    -0.20
    æĬĢæľ¯åĴĮ
    -0.20
    å¾Ĺå¾Ī好
    -0.19
    éĥ¨åī¯
    -0.19
    æĪij们çİ°åľ¨
    -0.19
    æŶéĹ´åĴĮ
    -0.19
    ä¸įè§ģäºĨ
    -0.19
    æľīçļĦ人
    -0.19
    POSITIVE LOGITS
     to
    0.34
    를
    0.20
     (...)
    0.20
     lakh
    0.20
    ìĹIJ
    0.19
    ìĿĦ
    0.19
     into
    0.19
    ãģ«
    0.19
    (...)↵
    0.19
    ACHER
    0.18
    Activations Density 0.343%

    No Known Activations