© 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. 61886
    Prev
    Next
    INDEX
    Explanations

    high morbidity and mortality

    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
    ardi
    -0.10
    æĹłæķ°æ¬¡
    -0.09
    çĥĺ
    -0.09
    æľĢåIJİä¸Ģ次
    -0.09
    æģ¨
    -0.09
    åĵ¥
    -0.08
     stead
    -0.08
     Bett
    -0.08
    obile
    -0.08
    æĦ¤
    -0.08
    POSITIVE LOGITS
    伤亡
    0.22
     casualties
    0.15
    æįŁå¤±
    0.14
    æŃ»äº¡
    0.13
     losses
    0.13
    æŃ»èĢħ
    0.13
     fatalities
    0.13
    人æŃ»äº¡
    0.12
     deaths
    0.12
    æįŁèĢĹ
    0.12
    Activations Density 0.107%

    No Known Activations