© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20857
    Prev
    Next
    INDEX
    Explanations

    end of life care""dying process""passed away peacefully""fear of death""work with the dying""assisted suicides""passed away peacefully""end-of-life process""help expected from nurses during the dying process""death education""dying and bereaved populations"

    np_acts-logits-general · gemini-2.5-flash-lite

    References to death, dying, end-of-life care, and hospice-related situations.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    为广大
    -0.11
    æĪ¢
    -0.11
    å¸ĤæķĻèĤ²
    -0.10
    rien
    -0.10
    UBLE
    -0.09
    ç¼§
    -0.09
    æĴĤ
    -0.09
    è¾Ł
    -0.09
    ocal
    -0.09
    åħħæ²Ľ
    -0.09
    POSITIVE LOGITS
     dying
    0.14
    æŃ»äº¡
    0.13
    临
    0.13
     death
    0.12
     hosp
    0.12
    death
    0.12
     Hosp
    0.12
    çļĦæľĢåIJİä¸Ģ
    0.11
    èĩ¨
    0.11
    æŃ»åIJİ
    0.11
    Activations Density 0.134%

    No Known Activations