© 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. 59292
    Prev
    Next
    INDEX
    Explanations

    first child, first favorite, first born

    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
    ä¸įåıĬ
    -0.09
    èĤ¯
    -0.09
    iken
    -0.08
    دار
    -0.08
     UPC
    -0.08
    é½IJ
    -0.08
    ich
    -0.08
    ifax
    -0.08
    骸
    -0.08
    çģµ
    -0.08
    POSITIVE LOGITS
    çĭ¬ä¸ĢæĹłäºĮ
    0.12
    çļĦè§Ĵèī²
    0.12
    è§Ĵèī²
    0.12
    带头
    0.11
    åľ¨ä¸Ģ个
    0.11
    åĶ¯ä¸Ģ
    0.11
    çĭ¬èĩª
    0.11
    主宰
    0.11
    æį¢æĿ¥
    0.10
    åĪ«äººçļĦ
    0.10
    Activations Density 0.098%

    No Known Activations