© 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. 26045
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and relations

    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
    èįĶæŀĿ
    -0.09
    åħ¨åĽ½äººæ°ij
    -0.08
    ä¹ŁåºĶ该
    -0.08
    ä¼łç»ŁçļĦ
    -0.08
    çļĦä¼łç»Ł
    -0.08
    åĢ¡è®®
    -0.08
    讨论
    -0.08
    æĸ½çŃĸ
    -0.08
    ocs
    -0.08
    举
    -0.08
    POSITIVE LOGITS
    å¦į
    0.10
    å±Ļ
    0.09
    éļ¶
    0.09
    ä¸Ńä»ĭ
    0.09
    æľĿ
    0.09
    åŃķ
    0.08
    åĮħ容
    0.08
    à¸ĵ
    0.08
     TBD
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    Activations Density 0.137%

    No Known Activations