© 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. 16724
    Prev
    Next
    INDEX
    Explanations

    FATAL EXCEPTION, sigterm, DNF

    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
    åįģä¸ĥæĿ¡
    -0.20
    åĪĪ
    -0.19
    ä¸īæĿ¡
    -0.19
    oru
    -0.19
    fest
    -0.18
    æŶèĬĤ
    -0.18
    ÑĮе
    -0.18
    æĺ¥å¤©
    -0.18
     schemes
    -0.18
    èĬĴ
    -0.18
    POSITIVE LOGITS
    ucher
    0.20
    ewan
    0.20
     воÑģ
    0.19
    ä¸ŃåĽ½ç§»åĬ¨
    0.19
     polish
    0.19
    frage
    0.19
     RVA
    0.19
    erie
    0.19
    楼ä¸Ĭ
    0.18
    ampoline
    0.18
    Activations Density 0.002%

    No Known Activations