© 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. 47723
    Prev
    Next
    INDEX
    Explanations

    sinusitis and rhinitis

    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
    èļ¤
    -0.09
    èĤ¡ä»·
    -0.08
     puls
    -0.08
    èĹĿ
    -0.08
    毯
    -0.08
     pt
    -0.08
    èµ°å¾Ĺ
    -0.08
    hung
    -0.08
     Pist
    -0.08
    ä¸ĢæĬĬ
    -0.08
    POSITIVE LOGITS
    ç¿ķ
    0.11
    aldo
    0.09
    åĿİ
    0.09
    éªħ
    0.09
    opensource
    0.09
    åı¤åħ¸
    0.09
    è¿Ļé¦ĸæŃĮ
    0.09
    idar
    0.09
    åĮĸçŁ³
    0.08
    é©·
    0.08
    Activations Density 0.030%

    No Known Activations