© 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. 24050
    Prev
    Next
    INDEX
    Explanations

    variation in organismsConfirms selfies

    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
    æĪijèĩªå·±
    -0.09
    çĶŁäº§è½¦éĹ´
    -0.09
    ä¹ĭäºī
    -0.09
    æĢİä¹Īåģļ
    -0.09
    åĨľä¸ļç§ijæĬĢ
    -0.09
    æĮijæĪĺ
    -0.09
    åķĨæľº
    -0.09
    åĨľä¸ļçĶŁäº§
    -0.09
    å©Ĩå©Ĩ
    -0.09
    æĢĿ绪
    -0.08
    POSITIVE LOGITS
    ÑĦон
    0.10
    å¹¿æ³Ľåħ³æ³¨
    0.08
    å´ĩ
    0.08
    èıĸ
    0.08
    èĺ¼
    0.07
    ï¾ŀ
    0.07
    èī¯å¥½çļĦ
    0.07
    ãĤĽ
    0.07
    RAL
    0.07
     STATS
    0.07
    Activations Density 0.036%

    No Known Activations