© 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. 36251
    Prev
    Next
    INDEX
    Explanations

    sudden death or passing

    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
    ç¾Ĭæ¯Ľ
    -0.11
    é«ĺåľ°
    -0.10
    æ³ŀ
    -0.09
    åĩıåħį
    -0.09
    gre
    -0.09
    çµ®
    -0.09
    wel
    -0.09
     добÑĢо
    -0.09
    æĥħ人èĬĤ
    -0.09
    æīĭæİĮ
    -0.09
    POSITIVE LOGITS
    æŃ»äº¡
    0.17
    çĮĿ
    0.14
    éĢĿ
    0.13
     mortality
    0.13
     death
    0.13
    身亡
    0.12
    æĤ²åī§
    0.12
     deaths
    0.12
    骤
    0.12
    death
    0.11
    Activations Density 0.158%

    No Known Activations