© 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. 13793
    Prev
    Next
    INDEX
    Explanations

    neither share nor sell

    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
    ä¸įè¦ģ太
    -0.25
    è¿ĺæĺ¯è¦ģ
    -0.19
    æľīæŶ
    -0.19
    éĢĤå®ľ
    -0.19
    ä¼łæĿ¥
    -0.19
    éľ²åĩº
    -0.18
     appropriate
    -0.18
    chl
    -0.18
    zek
    -0.18
    ä¸ĭæĿ¥
    -0.18
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.33
    æľīä»»ä½ķ
    0.30
    ä»»ä½ķ
    0.30
    ä»»ä½ķ人
    0.28
     anybody
    0.26
     anything
    0.25
    åĪ»æĦı
    0.25
     Ø¥ÙĦا
    0.24
     whatsoever
    0.23
     nor
    0.22
    Activations Density 0.011%

    No Known Activations