© 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. 59443
    Prev
    Next
    INDEX
    Explanations

    a or an before a noun

    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
     kind
    -0.09
    å¯Ŀ
    -0.09
    å¼Ģåĩº
    -0.08
    æĹħ
    -0.08
    kind
    -0.08
    妹
    -0.08
    UpDown
    -0.08
    ãħ£
    -0.08
    å°ıçĭĹ
    -0.08
    .Local
    -0.08
    POSITIVE LOGITS
    éĥ½æľīèĩªå·±
    0.09
    对åħ¶çľŁå®ŀ
    0.09
    äºİæѤ
    0.09
     trông
    0.09
    ä¸Ģ个好çļĦ
    0.09
    çļĦåIJĮæŶ
    0.09
    æĿŁ
    0.08
     взглÑıд
    0.08
    /effects
    0.08
    æĪIJ为ä¸Ģ个
    0.08
    Activations Density 0.074%

    No Known Activations