© 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. 16861
    Prev
    Next
    INDEX
    Explanations

    motility and manometry

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĻį
    -0.10
    èĢ³
    -0.09
    èĢģèĻİ
    -0.09
     ear
    -0.09
    åŃ£èĬĤ
    -0.08
    icl
    -0.08
    åħ»
    -0.08
    yper
    -0.08
    ç©·
    -0.08
    agal
    -0.08
    POSITIVE LOGITS
    cord
    0.10
    æĭīåĬ¨
    0.10
    åĿ¨
    0.10
    æľºåĬ¨
    0.10
    æİ¥åĬĽ
    0.10
     двиг
    0.09
    èģĶåĬ¨
    0.09
    æĸĩåĮĸåĪĽæĦı
    0.09
    æĽ¼åŁİ
    0.09
    ALSE
    0.09
    Activations Density 0.586%

    No Known Activations