© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10517
    Prev
    Next
    INDEX
    Explanations

    historical writings

    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
    Negative Logits
    æīĢæľīæĥħèĬĤ
    -0.27
    æĸ°äº¬
    -0.22
    å¤ĸç±į
    -0.22
    åľ¨ä»Ĭå¹´
    -0.22
     ÐĽÑİб
    -0.22
    ä¸Ńå°ı
    -0.22
    ä¸Ńå°ıä¼ģä¸ļ
    -0.21
     eskort
    -0.21
    å©į
    -0.21
     ActionType
    -0.21
    POSITIVE LOGITS
    æµģä¼ł
    0.24
    çºĤ
    0.23
     centuries
    0.23
     writings
    0.23
    åĪĽä½ľ
    0.23
    æĸĩ
    0.22
     writing
    0.22
     ëĭ¹ìĭľ
    0.21
    -era
    0.21
     original
    0.21
    Activations Density 0.023%

    No Known Activations