© 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. 39030
    Prev
    Next
    INDEX
    Explanations

    anesthesia and medical procedures

    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
    toa
    -0.10
    lish
    -0.10
    sworth
    -0.10
    åŁ´
    -0.09
    inding
    -0.09
    indy
    -0.08
    éħ±
    -0.08
    çļĦæĥħæĦŁ
    -0.08
    ipes
    -0.08
    ÑĪе
    -0.08
    POSITIVE LOGITS
    osc
    0.10
    ä¸įä½ı
    0.09
    lav
    0.09
    ãģĭãĤĬ
    0.09
    opensource
    0.09
    绪
    0.09
    èĸ
    0.09
    ç¨ĭ度
    0.08
    mart
    0.08
    ÑĢÑİ
    0.08
    Activations Density 0.048%

    No Known Activations