© 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. 693
    Prev
    Next
    INDEX
    Explanations

    daily activities and everyday life

    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
    volent
    -0.10
    æĿĢ害
    -0.09
    vir
    -0.09
    æijĩ头
    -0.09
     Horde
    -0.09
     اÙĦبÙĦ
    -0.09
    é«Ń
    -0.09
    emet
    -0.08
    æı
    -0.08
    ä»»
    -0.08
    POSITIVE LOGITS
    æĹ¥å¸¸çĶŁæ´»
    0.32
    æĹ¥å¸¸
    0.29
    çĶŁæ´»ä¸Ń
    0.27
     everyday
    0.26
    çĶŁæ´»
    0.23
    çĶŁæ´»çļĦ
    0.21
     Everyday
    0.20
    æĹ¥å¸¸å·¥ä½ľ
    0.19
    åľ¨çĶŁæ´»ä¸Ń
    0.18
    çİ°å®ŀçĶŁæ´»
    0.17
    Activations Density 0.088%

    No Known Activations