© 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. 23095
    Prev
    Next
    INDEX
    Explanations

    urinary tract and surgery

    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
    çĸı
    -0.11
     bootstrap
    -0.09
    åĮĿ
    -0.09
     Bootstrap
    -0.09
    æīĭæİĮ
    -0.09
    ä¼łæİĪ
    -0.09
    Boot
    -0.09
    -bootstrap
    -0.08
    boot
    -0.08
    篱
    -0.08
    POSITIVE LOGITS
    rophy
    0.10
    éĵ¸
    0.09
    ç»ĵçŁ³
    0.09
    _testing
    0.09
    .osgi
    0.08
    çĪ±ä¸Ĭ
    0.08
     Franz
    0.08
     ejac
    0.08
    erca
    0.08
     Void
    0.08
    Activations Density 0.287%

    No Known Activations