© 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. 31959
    Prev
    Next
    INDEX
    Explanations

    respiratory control ventilation

    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
    mers
    -0.09
    avel
    -0.09
    婺
    -0.09
    æľīåĪ©
    -0.09
    æĸ°ä¸ī
    -0.09
    çļ¤
    -0.09
     Parad
    -0.08
    èĨ»
    -0.08
    åħ¥æīĭ
    -0.08
    æ¢ħèĬ±
    -0.08
    POSITIVE LOGITS
    èµ·ä¼ı
    0.10
    é¢ijçİĩ
    0.10
    ITU
    0.09
    åĪ»èĭ¦
    0.09
     кÑĢов
    0.09
    ç°§
    0.09
    夫
    0.08
    .animate
    0.08
    æĮĩæłĩ
    0.08
    ext
    0.08
    Activations Density 0.200%

    No Known Activations