© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    additional bonus tracks

    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
    ä¸įåIJĮç±»åŀĭ
    -0.21
    ä¸Ģåıª
    -0.20
    ç¾½æ¯Ľ
    -0.20
    è¿Ļåıª
    -0.19
    å¹³åĿĩæ¯ı
    -0.19
    çijĽ
    -0.19
    çļĦåķĨåĵģ
    -0.19
    spd
    -0.18
    ãģĹãģĭãģªãģĦ
    -0.18
    _Abstract
    -0.18
    POSITIVE LOGITS
    é¢Ŀå¤ĸ
    0.28
    æĸ°çļĦ
    0.27
     additional
    0.23
    æĸ°åĮº
    0.23
    æĸ°å¢ŀ
    0.22
    æĸ°ãģŁ
    0.22
     ones
    0.22
     zusätzlich
    0.22
    æĸ°æĿIJæĸĻ
    0.21
     new
    0.21
    Activations Density 0.100%

    No Known Activations