© 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. 17871
    Prev
    Next
    INDEX
    Explanations

    type 2 diabetes mellitus

    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
     SEL
    -0.09
    æĴŀ
    -0.09
    æīĵæī®
    -0.09
    ACEMENT
    -0.09
    ë³´
    -0.09
     unh
    -0.09
    .getenv
    -0.08
     ÑĥÑĩеб
    -0.08
     camper
    -0.08
    vern
    -0.08
    POSITIVE LOGITS
    ç³ĸå°¿çĹħ
    0.15
    å¿ĥèĦıçĹħ
    0.13
    ç³ĸå°¿
    0.13
    è¡Ģç³ĸ
    0.11
    é«ĺè¡Ģåİĭ
    0.11
    å¿ĥè¡Ģ管
    0.11
     ÑģаÑħаÑĢ
    0.10
     diabetes
    0.10
    äºĮæľŁ
    0.10
    æħ¢æĢ§
    0.10
    Activations Density 0.241%

    No Known Activations