© 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. 4800
    Prev
    Next
    INDEX
    Explanations

    gynecology and obstetrics

    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
    饮
    -0.09
    ucha
    -0.09
    éħįæľī
    -0.09
    é¼ł
    -0.09
    ../../../
    -0.09
    ashboard
    -0.08
    ITIONAL
    -0.08
    aney
    -0.08
    æ±Ģ
    -0.08
    ouri
    -0.08
    POSITIVE LOGITS
    ваÑĢ
    0.09
    ount
    0.08
    丰满
    0.08
    æħ·
    0.08
    丼
    0.08
    losed
    0.08
    绽
    0.08
    èĬ±å¼Ģ
    0.08
    æŀľçĦ¶
    0.08
    ean
    0.08
    Activations Density 0.003%

    No Known Activations