© 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. 64025
    Prev
    Next
    INDEX
    Explanations

    by-products and waste

    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
    åĤ¨å¤ĩ
    -0.11
    åĪĨå·¥
    -0.10
    åĮ»åĬ¡äººåijĺ
    -0.10
    ç¾ŀ
    -0.10
    áĢī
    -0.09
    马æĭī
    -0.09
    antal
    -0.09
     CFL
    -0.09
    æĶ¯æĮģåĬĽåº¦
    -0.09
    .sharedInstance
    -0.09
    POSITIVE LOGITS
    å¤į
    0.09
     Fried
    0.09
    åĵĤ
    0.09
    综åIJĪåĪ©çĶ¨
    0.08
    iven
    0.08
     Ire
    0.08
    è¿Ļä¹Ī说
    0.08
    ker
    0.07
     inevitable
    0.07
    ivec
    0.07
    Activations Density 0.099%

    No Known Activations