© 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. 5951
    Prev
    Next
    INDEX
    Explanations

    Staphylococcus aureus

    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
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    -0.10
    èĬ¡
    -0.09
     BAT
    -0.09
    æł¹æį®èĩªå·±
    -0.09
    exampleInput
    -0.09
    ä¼ŀ
    -0.08
    ndo
    -0.08
     Surveillance
    -0.08
    tera
    -0.08
     bland
    -0.08
    POSITIVE LOGITS
    iliary
    0.09
    åī²
    0.09
    åĪĨåī²
    0.09
     Sok
    0.09
    äºī龸
    0.08
    èĦ¸é¢Ĭ
    0.08
    éĢĬ
    0.08
    麦
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
     Nak
    0.08
    Activations Density 0.089%

    No Known Activations