© 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. 23962
    Prev
    Next
    INDEX
    Explanations

    household chores and cleaning

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åı£æ°´
    -0.10
    ç»Ī身
    -0.09
    粪
    -0.09
    çIJ¢
    -0.09
    åģļ强
    -0.09
    åĽ´è§Ĥ
    -0.09
    ä¸Ģçĵ¶
    -0.08
    èķĸ
    -0.08
    è¶Ĭåıij
    -0.08
    åij³
    -0.08
    POSITIVE LOGITS
    æĹĭ
    0.09
    éļIJå½¢
    0.09
    uth
    0.09
    æĥº
    0.09
     Pitt
    0.08
    ä¹ĥ
    0.08
    ä½İ声
    0.08
    ä¸Ńå¤ĸ
    0.08
     Monkey
    0.08
    ãĤ¿ãĤ¤
    0.08
    Activations Density 0.018%

    No Known Activations