© 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. 15431
    Prev
    Next
    INDEX
    Explanations

    ways to improve business

    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
    æĪĸèĢħ说
    -0.23
    ä¸Ģæĺ¯
    -0.22
    fos
    -0.21
    ãģ§ãģĻãģĹ
    -0.20
    类似çļĦ
    -0.20
    ä¸ĢéĿ¢
    -0.19
    ãĥŁãĥ¥
    -0.18
    çŁŃæĿ¿
    -0.18
    ä¹Łæĺ¯å¦ĤæѤ
    -0.18
    riba
    -0.18
    POSITIVE LOGITS
     etc
    0.31
    çŃīçŃī
    0.29
    etc
    0.28
    è¿ĻäºĽéĥ½æĺ¯
    0.28
     ultimately
    0.26
    çŃīæĸ¹éĿ¢
    0.23
    çŃīå·¥ä½ľ
    0.22
     dam
    0.21
    ives
    0.21
     cả
    0.21
    Activations Density 0.922%

    No Known Activations