© 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. 60698
    Prev
    Next
    INDEX
    Explanations

    coming-of-age and ending phrases

    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
    æĸ¹ä¾¿
    -0.10
    æĪIJ份
    -0.08
    åĿĩçĶ±
    -0.08
    odem
    -0.08
     apparently
    -0.08
    人éĥ½
    -0.08
    _REGISTRY
    -0.08
     Ø£ÙĦÙģ
    -0.08
    fort
    -0.08
    spi
    -0.08
    POSITIVE LOGITS
    æľīçļĦ
    0.09
    åŃIJéĩĮ
    0.09
     Welch
    0.09
    æīĺ管
    0.08
    æĮ¹
    0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    0.08
    icals
    0.08
    åŃIJå¼Ł
    0.08
    äºĶæĺŁ
    0.08
     stringent
    0.08
    Activations Density 0.002%

    No Known Activations