© 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. 13990
    Prev
    Next
    INDEX
    Explanations

    clinical management and decisions

    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
    æĮº
    -0.23
    è´§
    -0.22
    src
    -0.21
    åħ¬åħ±æĸĩåĮĸ
    -0.21
    æĴº
    -0.21
    峪
    -0.20
    çľ¼æ³ª
    -0.19
    à¸Ńà¸ĩ
    -0.19
    æĬĬèĩªå·±çļĦ
    -0.19
    æĶ¿åºľ
    -0.19
    POSITIVE LOGITS
    æī§ä¸ļ
    0.23
    æİ¥æīĭ
    0.22
     Ча
    0.22
    æĸĩçĮ®
    0.22
     cases
    0.21
    éģµå¾ª
    0.21
     encountered
    0.21
    临åºĬ
    0.21
    å¤ĦçIJĨ
    0.21
    è§ĦèĮĥ
    0.21
    Activations Density 0.473%

    No Known Activations