© 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. 10320
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
     ones
    -0.20
    èįīæ¡Ī
    -0.18
    çľ¼ä¸ĭ
    -0.17
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.17
    sis
    -0.17
    èį¸
    -0.17
     ÐŁÐµÑĤ
    -0.17
    æ¯Ķå¦Ĥ
    -0.17
    _movie
    -0.16
     /^(
    -0.16
    POSITIVE LOGITS
    à¹Ģà¸Ńà¸ĩ
    0.23
    ฯ
    0.23
    æīĢåľ¨çļĦ
    0.22
    åĴĮä»ĸçļĦ
    0.20
    æľ¬äºº
    0.19
    çļĦä¸ĢåĪĩ
    0.19
    çī
    0.19
    inia
    0.19
    æĭĽå¾ħ
    0.18
     stesso
    0.18
    Activations Density 0.128%

    No Known Activations