© 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. 47415
    Prev
    Next
    INDEX
    Explanations

    like so

    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
    äºĨå¾Īä¹ħ
    -0.10
    足足
    -0.10
    uitive
    -0.10
    sic
    -0.10
     ведÑĮ
    -0.09
    ç½Ħ
    -0.09
    èµ·çłģ
    -0.09
     propTypes
    -0.09
    å¾Ī大
    -0.09
    пÑĥÑģка
    -0.09
    POSITIVE LOGITS
    aments
    0.10
    ä¸Ģå°ı
    0.09
    alls
    0.09
     Gron
    0.09
    arl
    0.09
     acc
    0.08
    añ
    0.08
    è½»è½»åľ°
    0.08
    .imp
    0.08
    estr
    0.08
    Activations Density 0.003%

    No Known Activations