© 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. 639
    Prev
    Next
    INDEX
    Explanations

    layoffs and redundancy

    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
    éªĿ
    -0.10
    éģģ
    -0.10
    å°¼äºļ
    -0.09
    ReadStream
    -0.09
    æľ¨åľ°æĿ¿
    -0.09
    æIJ¬åĪ°
    -0.09
    åī¥å¤º
    -0.09
    æĭįæĭį
    -0.09
    åįģ足
    -0.09
    alist
    -0.09
    POSITIVE LOGITS
    Dar
    0.10
    l
    0.08
    榷
    0.08
    lk
    0.08
    鸦
    0.08
    ноÑģÑĤей
    0.08
     ÑįкономиÑĩеÑģк
    0.08
     маÑĤеÑĢи
    0.08
     trÃŃ
    0.07
    enes
    0.07
    Activations Density 0.010%

    No Known Activations