© 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. 833
    Prev
    Next
    INDEX
    Explanations

    realized/realised that

    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
    åĹ£
    -0.10
    å¾Īå¿«å°±
    -0.10
    æŀ¶
    -0.09
    æī¾åĪ°
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
    azar
    -0.08
    éģĤ
    -0.08
    æĬĵä½ı
    -0.08
    å¾Īå¿«
    -0.08
     giÃłnh
    -0.08
    POSITIVE LOGITS
    åıĪè¦ģ
    0.11
    ä»İåݻ年
    0.10
    å·²ç»ıæľī
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    pbs
    0.09
    ÑĤоп
    0.09
    æĺ¯å¤ļä¹Ī
    0.09
    ä¹Łè¦ģ
    0.09
    åķĨæľº
    0.09
    åģļçļĦ
    0.09
    Activations Density 0.048%

    No Known Activations