© 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. 4756
    Prev
    Next
    INDEX
    Explanations

    stroke and cerebrovascular disease

    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
    è¹Ļ
    -0.10
    mes
    -0.09
    apas
    -0.08
    å¹½
    -0.08
    ODB
    -0.08
    inning
    -0.08
    书éĻ¢
    -0.08
     pers
    -0.08
    åıijå±ķåīįæĻ¯
    -0.08
     Seymour
    -0.08
    POSITIVE LOGITS
    鬼
    0.10
    èĩªçĦ¶èĢĮçĦ¶
    0.09
     stroke
    0.09
     PRIV
    0.09
    åĪ·
    0.09
     geg
    0.09
    çļĦç»ıåİĨ
    0.09
    -strokes
    0.09
    缤
    0.09
    çªģçĦ¶
    0.08
    Activations Density 0.134%

    No Known Activations