© 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. 40035
    Prev
    Next
    INDEX
    Explanations

    fungal infections and conditions

    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
     Reception
    -0.09
    å£ķ
    -0.09
    sg
    -0.09
    èIJ½æĪ·
    -0.09
    ä»»
    -0.09
    çľ¼æ³ª
    -0.09
    angi
    -0.09
    ä¸įåħĭä¸įåıĬ
    -0.08
    棱
    -0.08
     اÙĦشرÙĬÙģ
    -0.08
    POSITIVE LOGITS
    æīij
    0.10
    åıĭ好
    0.09
     fungal
    0.08
    æ²»çIJĨ
    0.08
    iten
    0.08
    èĽĢ
    0.08
    éħµ
    0.08
    requ
    0.08
    ç§ĥ
    0.08
    unities
    0.08
    Activations Density 0.109%

    No Known Activations