© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    closing decision or overtime

    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
    toc
    -0.09
     вообÑīе
    -0.09
    ä»ĸå·²ç»ı
    -0.09
    å¤§åĽ½
    -0.08
    åįıåIJĮ
    -0.08
    å·²ç»ıæľīäºĨ
    -0.08
    对ä»ĸ们
    -0.07
     already
    -0.07
    主ä¸ļ
    -0.07
     deduct
    -0.07
    POSITIVE LOGITS
    åħ¨åľº
    0.10
    çĬ¶æĢģä¸ĭ
    0.09
    æľºåĪ¶
    0.08
     Hour
    0.08
    hausen
    0.08
    ä¸įèĪį
    0.08
    åģĵ
    0.08
     اÙĦتش
    0.08
    æĥĭ
    0.08
    åĨľåľº
    0.08
    Activations Density 0.016%

    No Known Activations