© 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. 12328
    Prev
    Next
    INDEX
    Explanations

    workplace and work environment

    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
    å½ĵæĻļ
    -0.10
    溺
    -0.09
     RESP
    -0.09
    æľĥåĵ¡
    -0.09
     Tonight
    -0.08
    _PORTS
    -0.08
    åģļ大
    -0.08
    .resp
    -0.08
    obil
    -0.08
    ç©Ĺ
    -0.08
    POSITIVE LOGITS
    åIJĮäºĭ
    0.17
    ä¸Ĭåı¸
    0.17
    èģĮåľº
    0.16
    åijĺå·¥
    0.16
    åľ¨èģĮ
    0.15
    åĬŀåħ¬å®¤
    0.15
    åIJĮäºĭ们
    0.15
    离èģĮ
    0.14
    ä¼ģä¸ļæĸĩåĮĸ
    0.14
    åħ¥èģĮ
    0.13
    Activations Density 0.149%

    No Known Activations