© 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. 11827
    Prev
    Next
    INDEX
    Explanations

    article or story

    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
    æ»ĵ
    -0.20
    åĪĩéĻ¤
    -0.19
    ieder
    -0.18
    椰
    -0.18
    åħ±åIJĮä½ĵ
    -0.18
    éĩī
    -0.17
    лов
    -0.17
    对èĩªå·±
    -0.17
    ä¸įå®ļ
    -0.17
    ÑĦи
    -0.17
    POSITIVE LOGITS
    éħ·
    0.21
    upo
    0.20
    æݢ讨
    0.20
    æİ¢
    0.20
     Alv
    0.20
    æıIJåĪ°
    0.19
    SPATH
    0.19
    å¼ĢåĬŀ
    0.19
    æĬ¥éģĵ
    0.19
    æıIJåıĬ
    0.19
    Activations Density 0.054%

    No Known Activations