© 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. 678
    Prev
    Next
    INDEX
    Explanations

    end of a sentence or clause

    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
    åģļ个
    -0.10
    æĪIJè´¥
    -0.10
    unt
    -0.09
    æĢ¡
    -0.09
    lobs
    -0.09
    lest
    -0.09
    æĮ¥æīĭ
    -0.08
    atron
    -0.08
    eler
    -0.08
    ãĥ¼ãĤ¹
    -0.08
    POSITIVE LOGITS
    íģIJ
    0.09
    lij
    0.09
    ä¿®åħ»
    0.09
    ê¼´
    0.09
    ä¸ĵéŨ
    0.08
    æĿ¥çĶµ
    0.08
    æĽ¾åľ¨
    0.08
    jah
    0.08
    å¤ļå¹´çļĦ
    0.08
     switched
    0.08
    Activations Density 0.271%

    No Known Activations