© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3411
    Prev
    Next
    INDEX
    Explanations

    that we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    éĿ¢ç§¯çº¦
    -0.26
    æľīè¶³å¤ŁçļĦ
    -0.25
    å¾Īæ¸ħæ¥ļ
    -0.23
    wise
    -0.23
    å¾Īç®Ģåįķ
    -0.23
    ä»Ģä¹Īéĥ½
    -0.23
     enough
    -0.22
    çļĦéĩįçĤ¹
    -0.22
    çļĦä¸ĢåĪĩ
    -0.22
    让æ¶Īè´¹èĢħ
    -0.22
    POSITIVE LOGITS
    åŃĺåľ¨äºİ
    0.28
    æĪijä»¬åľ¨
    0.28
    æĪij们
    0.27
    æĪij们çļĦ
    0.27
     encountered
    0.26
     our
    0.25
     present
    0.25
     eman
    0.25
    åĩºèĩª
    0.24
    åĩºçİ°åľ¨
    0.24
    Activations Density 0.093%

    No Known Activations