© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19005
    Prev
    Next
    INDEX
    Explanations

    organ transplant rejection

    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
    èĭŁ
    -0.09
    çıłæ±Ł
    -0.08
    å°ıé¾Ļ
    -0.08
     tempered
    -0.08
    æīİ
    -0.08
    venes
    -0.08
    Leaks
    -0.08
     impres
    -0.08
    å¸ĮæľĽèĥ½
    -0.08
    Reading
    -0.08
    POSITIVE LOGITS
    æİĴæĸ¥
    0.17
     rejection
    0.11
    foreign
    0.11
    æİ¥åıĹäºĨ
    0.09
    失è°ĥ
    0.09
    host
    0.09
    ä¸Ģå¾ĭ
    0.09
     Identity
    0.09
    éĽĴ
    0.09
    .ali
    0.09
    Activations Density 0.218%

    No Known Activations