© 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. 11961
    Prev
    Next
    INDEX
    Explanations

    you are/you're

    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
    åı²è¯Ĺ
    -0.17
    ä½łèĩªå·±
    -0.17
    urre
    -0.17
    æĬĬä½ł
    -0.17
    Ordinal
    -0.17
    éĵ¢
    -0.17
    æĢ»èĢĮè¨Ģ
    -0.17
    util
    -0.16
    esus
    -0.16
    çļĦå½¢å¼ı
    -0.16
    POSITIVE LOGITS
    å¸ĺ
    0.19
    误ä¼ļ
    0.18
    æĪijçļĦ
    0.18
    æ¯ķç«Łæĺ¯
    0.18
    ãģ¹ãģį
    0.17
    peÅĤ
    0.17
    å¹²éĥ¨èģĮå·¥
    0.17
     ведÑĮ
    0.16
    åł¡
    0.16
     DBG
    0.16
    Activations Density 0.037%

    No Known Activations