© 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. 24211
    Prev
    Next
    INDEX
    Explanations

    random draws and selections

    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
    æĸĻ
    -0.11
    è¿İåIJĪ
    -0.10
    ofire
    -0.10
    oten
    -0.09
    峡
    -0.09
    amide
    -0.09
     Mist
    -0.09
     ÐĿи
    -0.09
    è¦ģåѦä¼ļ
    -0.09
    ãĥĪãĥ«
    -0.09
    POSITIVE LOGITS
    éļıæľº
    0.24
     random
    0.19
     Random
    0.18
    .random
    0.18
    æĬ½åıĸ
    0.18
    random
    0.18
    Random
    0.17
    æĬ½å¥ĸ
    0.17
     RANDOM
    0.17
    éĺĦ
    0.16
    Activations Density 0.057%

    No Known Activations