© 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. 60743
    Prev
    Next
    INDEX
    Explanations

    special characters and web file extensions

    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
    çĴ
    -0.11
    éĺħ读åħ¨æĸĩ
    -0.10
    çĸ
    -0.09
    èIJ
    -0.09
    纪
    -0.08
    /animations
    -0.08
    åĤij
    -0.08
    æĺ¯æĪijçļĦ
    -0.08
     Lawson
    -0.08
    çļĦ妻åŃIJ
    -0.08
    POSITIVE LOGITS
     Wol
    0.08
    æݬ
    0.08
    ügen
    0.08
    å¸Ĩ
    0.08
     coun
    0.08
    ç»Ģ
    0.08
    缯
    0.08
    onta
    0.08
    å¼¥
    0.08
    äl
    0.08
    Activations Density 0.145%

    No Known Activations