© 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. 17053
    Prev
    Next
    INDEX
    Explanations

    McCormack, Scarff, Lockhart, Mourey, Ortega, Larsen

    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
    éĻĦè¿ijçļĦ
    -0.18
    çļĦ好
    -0.18
    çļĦæĸ°
    -0.17
    è¿ĺ
    -0.17
     Barcl
    -0.17
    èĢħçļĦ
    -0.17
    å»Ĭ
    -0.17
    \<^
    -0.17
    ç²¾åĵģ
    -0.17
     mükem
    -0.17
    POSITIVE LOGITS
    åĪĿæģĭ
    0.19
    ãģ¨ãģĦãģ£ãģŁ
    0.18
    é¦ģ
    0.18
    ç±´
    0.17
    ç¯ĵ
    0.17
    ä¿Ŀ驾æĬ¤
    0.17
    èĦ±åıij
    0.16
    ä¸ī大éĺ¶æ®µ
    0.16
    çŃīçŃī
    0.16
    å¼łæī¬
    0.16
    Activations Density 0.138%

    No Known Activations