© 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. 16639
    Prev
    Next
    INDEX
    Explanations

    results of clinical trials

    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
    ä¼ģä¸ļåĴĮ
    -0.23
    建设åĴĮ
    -0.21
     {}.
    -0.20
    ç»ıéªĮåĴĮ
    -0.20
    esp
    -0.20
    æīĢè°ĵçļĦ
    -0.19
    quals
    -0.19
    ìĿ´ê³ł
    -0.18
    åĢĵ
    -0.18
    yk
    -0.17
    POSITIVE LOGITS
    åĿĩ
    0.32
    çļĦ人éĥ½
    0.29
    éĥ½åľ¨
    0.29
    éĥ½æĺ¯
    0.28
     Äijá»ģu
    0.27
    人éĥ½
    0.27
    åĿĩæľī
    0.25
    éĥ½è¢«
    0.23
    çļĨ
    0.22
    éĥ½ä¼ļ
    0.22
    Activations Density 0.775%

    No Known Activations