© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7460
    Prev
    Next
    INDEX
    Explanations

    breathing and respiratory effort

    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
    ä¸Ģç«Ļ
    -0.11
    çħ§
    -0.10
    åĽŀ头
    -0.10
    åħĪ导
    -0.09
    éĽ¨æ°´
    -0.09
    çģĮ
    -0.09
    ç»ĵå®ŀ
    -0.08
    æ£ļ
    -0.08
    ä¸į容
    -0.08
    æ¸į
    -0.08
    POSITIVE LOGITS
    åij¼åIJ¸
    0.20
     breathing
    0.17
    Bre
    0.14
    åĸĺ
    0.14
     breath
    0.14
     Bre
    0.13
     breathe
    0.13
    åĶ¿
    0.12
    -bre
    0.12
     respir
    0.12
    Activations Density 0.073%

    No Known Activations