© 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. 11861
    Prev
    Next
    INDEX
    Explanations

    erase board or whiteboard application

    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
    æĮģãģ¡
    -0.21
    ä½ľé£İ建设
    -0.19
    sov
    -0.18
     OD
    -0.18
    osex
    -0.18
    lemen
    -0.18
    è¿Ŀ
    -0.18
    BED
    -0.18
    è¯¥é¡¹çĽ®
    -0.17
    ç»Ĩ
    -0.17
    POSITIVE LOGITS
    èĴľ
    0.23
    å¢ĻéĿ¢
    0.20
    SMART
    0.20
    (factory
    0.19
    ç¬Ĩ
    0.19
    æķĻ室
    0.18
    æĮ½
    0.18
    æݨçIJĨ
    0.18
    æ¼Ķ
    0.18
     cust
    0.18
    Activations Density 0.007%

    No Known Activations