© 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. 59466
    Prev
    Next
    INDEX
    Explanations

    nicknames in quotes

    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
    ushed
    -0.10
    è¡Ģ
    -0.09
    iveau
    -0.09
    æ¯Ķäºļ
    -0.09
    wen
    -0.09
    大åĪĩãģª
    -0.08
    梨
    -0.08
    æ¸Ĺ
    -0.08
    .side
    -0.08
    FormField
    -0.08
    POSITIVE LOGITS
    åıĶ
    0.09
    ä¸Ģåı·
    0.09
     Hobby
    0.09
    æİı
    0.09
    åıĶåıĶ
    0.08
    ãĤ«ãĥª
    0.08
    æ±Ĥå©ļ
    0.08
    åįļ主
    0.08
    称åı·
    0.08
     himself
    0.08
    Activations Density 0.069%

    No Known Activations