© 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. 49820
    Prev
    Next
    INDEX
    Explanations

    death 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
    è·¬
    -0.10
    .voice
    -0.10
    åıijå±ķä¸Ń
    -0.09
    éºĤ
    -0.09
    æĭĩæĮĩ
    -0.09
    éĽªèĬ±
    -0.08
    çļĦçĶ·äºº
    -0.08
    æ´²
    -0.08
    ç¨Ĺ
    -0.08
    åħ´ä¸ļ
    -0.08
    POSITIVE LOGITS
    æŃ»äº¡
    0.20
     death
    0.18
     Death
    0.16
    death
    0.16
    -death
    0.16
     mortality
    0.16
    _death
    0.15
    Death
    0.14
    çĶŁåij½çļĦ
    0.14
    çĶŁåij½
    0.14
    Activations Density 0.092%

    No Known Activations