© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10541
    Prev
    Next
    INDEX
    Explanations

    years or time

    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
    Negative Logits
    çļĦä¸ĢåĪĩ
    -0.21
    尽快
    -0.19
    æĸ¹éĿ¢çļĦ
    -0.19
    ECH
    -0.18
    ä¹Łå¥½
    -0.18
    æĸ°ä¸Ģ代
    -0.17
    æĶ¾æīĭ
    -0.17
    èµĦè´¨
    -0.17
    çļĦæīĢæľī
    -0.17
    æĹ¥åIJİ
    -0.17
    POSITIVE LOGITS
    以æĿ¥
    0.33
     ago
    0.30
    以ä¾Ĩ
    0.27
    ä¸Ģ缴æĺ¯
    0.26
    å·²ä¹ħ
    0.26
    ä¸Ģ缴éĥ½
    0.24
    ä¸Ģ缴éĥ½æĺ¯
    0.22
    ä¸Ģ缴
    0.22
    åĽ°æī°
    0.21
    aret
    0.21
    Activations Density 0.043%

    No Known Activations