© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12356
    Prev
    Next
    INDEX
    Explanations

    describing attributes and qualities

    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
    æĺ¯ä¸ĢåIJį
    -0.29
    æĺ¯ä¸Ģ款
    -0.27
    æĺ¯ä¸Ģ座
    -0.27
    æĺ¯ä¸Ģä½į
    -0.27
    ä¸Ģ个å°ı
    -0.27
    ä¸Ģ个æĸ°çļĦ
    -0.25
    ä¸Ģä½į
    -0.24
    çļĦä¸Ģ款
    -0.24
    æĺ¯ä¸Ģç§į
    -0.23
    ä¸ĢåIJį
    -0.23
    POSITIVE LOGITS
    缸继
    0.24
     themselves
    0.23
    åIJĦå¼Ĥ
    0.20
    ниÑĩ
    0.20
    ëĵ¤ìĿĦ
    0.20
    és
    0.19
    ä¸įåIJĮç¨ĭ度
    0.19
    Ñģад
    0.19
    rites
    0.19
    ëĵ¤
    0.19
    Activations Density 1.120%

    No Known Activations