© 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. 47621
    Prev
    Next
    INDEX
    Explanations

    the and the like

    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
    çļĦéĤ£ç§į
    -0.11
    éĤ£ç§į
    -0.10
    çļĦéĤ£ä¸ª
    -0.09
     окÑĢÑĥжа
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
    oure
    -0.08
    åĪ«çļĦ
    -0.08
     главное
    -0.08
    åIJĦç§įåIJĦæł·
    -0.08
     дÑĢÑĥгиÑħ
    -0.08
    POSITIVE LOGITS
    æŃ¤ä¸¾
    0.12
     latter
    0.12
    äºĮèĢħ
    0.11
    ä¸Ģéģĵ
    0.10
    åħ¶å®ŀ
    0.10
    涣
    0.10
    åĿ¨
    0.10
    两èĢħ
    0.09
    岸
    0.09
    æĺĶæĹ¥
    0.09
    Activations Density 0.509%

    No Known Activations