© 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. 59183
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    çħ§é¡¾
    -0.09
    æīĵçĿĢ
    -0.09
    åŁŁ
    -0.09
    身åŃIJ
    -0.08
    笼
    -0.08
    家åħ·
    -0.08
     ([[
    -0.08
    åij¦
    -0.08
    _ud
    -0.08
    æīĵäºĨ
    -0.08
    POSITIVE LOGITS
    åŃĢ
    0.11
    åį¡æĭī
    0.10
    çIJ¼
    0.09
    èµĮ
    0.09
     tune
    0.09
    geb
    0.09
    å¹²äºĭåĪĽä¸ļ
    0.09
     Married
    0.09
    èį«
    0.08
    æ²ĸ
    0.08
    Activations Density 0.080%

    No Known Activations