© 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. 3130
    Prev
    Next
    INDEX
    Explanations

    Iran, Islamic Republic, antibody response

    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
    éħ£
    -0.10
     Cath
    -0.10
    å±ģèĤ¡
    -0.09
    寥
    -0.09
    æī¯
    -0.09
    楼ä¸Ĭ
    -0.09
    uchen
    -0.09
    chter
    -0.09
    eso
    -0.09
    æīĭæİĮ
    -0.09
    POSITIVE LOGITS
    毯
    0.10
    æĿĵ
    0.09
    æģĴ
    0.09
    åĮ»çĸĹæľįåĬ¡
    0.08
     Ensemble
    0.08
    ä¿Ŀ管
    0.08
    è¿ĽæĿ¥
    0.08
    æģ
    0.08
    åĽ½åĨħå¸Ĥåľº
    0.08
    ä¼ı
    0.08
    Activations Density 0.267%

    No Known Activations