© 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. 2087
    Prev
    Next
    INDEX
    Explanations

    urinary incontinence

    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
    åİķæīĢ
    -0.12
    粪
    -0.11
    åIJIJ
    -0.11
     toilet
    -0.10
    æµ´
    -0.10
    (coder
    -0.10
    æĴĴ
    -0.10
     Kick
    -0.10
    马桶
    -0.09
     sink
    -0.09
    POSITIVE LOGITS
    aska
    0.10
    ä¿Ŀå§Ĩ
    0.09
    BorderColor
    0.09
    åºķæ°Ķ
    0.09
    éļĶå£ģ
    0.08
    3
    0.08
    临è¿ij
    0.08
    éļĶçĥŃ
    0.08
    uzu
    0.08
     Gig
    0.08
    Activations Density 0.113%

    No Known Activations