© 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. 829
    Prev
    Next
    INDEX
    Explanations

    boxing matches or tournaments

    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
    ToFront
    -0.11
    离
    -0.10
    erus
    -0.10
    éĽ¢
    -0.10
    æIJŃéħį
    -0.09
    åıijå±ķ缮æłĩ
    -0.09
    quot
    -0.09
    æĻĤçĤ¹ãģ§
    -0.09
     quot
    -0.09
    SURE
    -0.09
    POSITIVE LOGITS
    è¿Ī
    0.10
    åĮį
    0.09
    æĮ£æīİ
    0.09
    aron
    0.09
    æĬ±ä½ı
    0.08
    entes
    0.08
    éĺ¶æ¢¯
    0.08
    æłĢ
    0.08
    å¹´éĻIJ
    0.08
     Scor
    0.08
    Activations Density 0.073%

    No Known Activations