© 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. 15922
    Prev
    Next
    INDEX
    Explanations

    creature damage, opportunity attacks, cards

    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
    çĽ¸å¯¹æĿ¥è¯´
    -0.22
    iem
    -0.21
    ier
    -0.21
     bits
    -0.19
     kind
    -0.19
     variations
    -0.19
    æĿ¥åĽŀ
    -0.19
     quite
    -0.19
     comparatively
    -0.19
    è°£
    -0.19
    POSITIVE LOGITS
    ä¸įå°ijäºİ
    0.23
    符åIJĪæĿ¡ä»¶
    0.23
    åľ¨çݩ家ä¸Ń
    0.23
    æĮģæľīçļĦ
    0.22
    è§Ĩ为
    0.20
    ä¸ŃåĽ½ç½ij游
    0.20
    æĮĩå®ļ
    0.20
     showc
    0.20
     Jeżeli
    0.20
    éĩıåĮĸ
    0.19
    Activations Density 0.027%

    No Known Activations