© 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. 40169
    Prev
    Next
    INDEX
    Explanations

    cobra, cancer, virus

    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
    å¿¡
    -0.09
    å°±æĺ¯è¿Ļæł·
    -0.09
    esh
    -0.09
    é³Į
    -0.08
    褫
    -0.08
     lit
    -0.08
    éĥĬåĮº
    -0.08
    yan
    -0.08
    ราว
    -0.08
    Ñĩки
    -0.08
    POSITIVE LOGITS
    碼
    0.10
     внимание
    0.10
    æĢ»åħ¬åı¸
    0.10
    orz
    0.10
    æł·çļĦ
    0.10
    azon
    0.09
    맨
    0.09
    次æķ°
    0.09
    azzi
    0.09
    dorf
    0.09
    Activations Density 0.006%

    No Known Activations