© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35855
    Prev
    Next
    INDEX
    Explanations

    only if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    临
    -0.10
    èĩ¨
    -0.09
    èĬ®
    -0.09
     Damen
    -0.08
     Banc
    -0.08
    æĢİä¹Īåı¯èĥ½
    -0.08
    çī¹éķ¿
    -0.08
    erness
    -0.08
    觸
    -0.08
    MB
    -0.08
    POSITIVE LOGITS
    é¢ĦåħĪ
    0.10
    èµ·çłģ
    0.10
    åĺ´éĩĮ
    0.10
    ä¼´éļı
    0.10
    è¦ģä¹Ī
    0.09
    èĤ´
    0.09
    èĦijåŃIJéĩĮ
    0.09
    æľīæĦıæĢĿ
    0.09
    ä»Ģä¹Īåij¢
    0.09
    空æ°Ķè´¨éĩı
    0.09
    Activations Density 0.156%

    No Known Activations