© 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. 16828
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    åıĬ缸åħ³
    -0.09
    å°½
    -0.08
     Gim
    -0.08
    lection
    -0.08
    çģĮ
    -0.08
     нек
    -0.08
    缸åħ³åĨħ容
    -0.08
    atch
    -0.07
    bell
    -0.07
    æĺ¯ä¸ŃåĽ½
    -0.07
    POSITIVE LOGITS
    ä¹Łå¥½
    0.10
    ãĢģ
    0.10
    CLE
    0.09
    ä¹Łåıªæĺ¯
    0.09
    åĮ¯
    0.09
    ieran
    0.08
    ä»ĸ说
    0.08
    #/
    0.08
    -desc
    0.08
    .gc
    0.08
    Activations Density 0.616%

    No Known Activations