© 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. 29496
    Prev
    Next
    INDEX
    Explanations

    slow movement, Polish dances, lengthy pieces

    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
    éĴĿ
    -0.10
    æĺı
    -0.10
    ç½ijä¸Ĭ
    -0.10
    éļİ
    -0.10
    çŃ¾
    -0.09
    ç¼ĺåĪĨ
    -0.09
    æľīäºĽäºº
    -0.09
    åIJij社ä¼ļ
    -0.09
    对ä»ĸ们
    -0.09
    å¤ļä½Ļ
    -0.09
    POSITIVE LOGITS
    è¯Ńæ°Ķ
    0.08
    åºĶ注æĦı
    0.08
    åı¯ä¿¡
    0.08
     embroidered
    0.08
    .Builder
    0.08
    åħ¨æĿij
    0.08
    éļ¾çĤ¹
    0.08
    rub
    0.08
     climax
    0.08
    æĸ°æĿIJæĸĻ
    0.07
    Activations Density 0.030%

    No Known Activations