© 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. 24220
    Prev
    Next
    INDEX
    Explanations

    even 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
    ä½łä¼ļåıijçİ°
    -0.11
     probably
    -0.10
     há»ĵi
    -0.10
    ople
    -0.10
    åĩłä¹İæīĢæľī
    -0.10
    å·®ä¸įå¤ļ
    -0.10
    éĿŀ常å¤ļçļĦ
    -0.09
     zwar
    -0.09
    大æ¦Ĥ
    -0.09
    é¥
    -0.09
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.12
    æĺ¯ä»¥
    0.10
    æĺ¯ä¸ºäºĨ
    0.09
    æĺ¯çĶ±
    0.09
     Berk
    0.08
    æĺ¯ä»İ
    0.08
     apprec
    0.08
    åıªæĺ¯
    0.08
    åĪĿ次
    0.08
    UDO
    0.08
    Activations Density 0.028%

    No Known Activations