© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18705
    Prev
    Next
    INDEX
    Explanations

    urination and defecation

    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
    ç»Ĵ
    -0.09
     Pound
    -0.09
    stre
    -0.09
    ç»ĪçĶŁ
    -0.09
    ç½ķ
    -0.09
    åĩĢåĢ¼
    -0.08
    èµ·ä¼ı
    -0.08
    å¸ĮæľĽèĩªå·±
    -0.08
    åģļ强
    -0.08
    nett
    -0.08
    POSITIVE LOGITS
    жи
    0.09
    æ°®
    0.09
    feld
    0.09
    erator
    0.09
    å°¿
    0.09
    æµij
    0.09
    ç´ł
    0.08
    âĹ¯
    0.08
    jak
    0.08
    lion
    0.08
    Activations Density 0.101%

    No Known Activations