© 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. 10552
    Prev
    Next
    INDEX
    Explanations

    viewpoint

    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
    ãģ§ãģĤãĤįãģĨ
    -0.22
    读åIJİ
    -0.21
    äººåľ¨
    -0.21
    éĢļè¿ĩ对
    -0.21
    wit
    -0.20
    å¾Įãģ«
    -0.20
    ãģĨãģ¡ãģ«
    -0.20
    åĽŀåĪ°
    -0.20
    ç¼Ķ
    -0.20
    éĻĢ
    -0.19
    POSITIVE LOGITS
    æĿ¥è¯´
    0.31
    èĢĮè¨Ģ
    0.28
    ä»ĸæĺ¯ä¸Ģ个
    0.25
    ä¾Ĩ說
    0.24
    æĿ¥è®²
    0.23
     speaking
    0.23
    æĺ¯ä¸Ģ件
    0.22
    è¿Ļæĺ¯
    0.22
     nothing
    0.21
    ä»ĸ们æĺ¯
    0.21
    Activations Density 0.082%

    No Known Activations