© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13104
    Prev
    Next
    INDEX
    Explanations

    deaths and mortality yearly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ruit
    -0.20
     Hindered
    -0.19
    ernes
    -0.19
    æĪIJéķ¿ä¸º
    -0.18
    âĸ¹
    -0.17
    ãģ«åĩº
    -0.17
    åĿĩ使åħ¶
    -0.17
    _echo
    -0.17
    çĶ·åŃ©åŃIJ
    -0.17
    à¸Ĺร
    -0.17
    POSITIVE LOGITS
    çİĩ
    0.25
    -death
    0.22
     death
    0.21
     deaths
    0.21
     toll
    0.20
    aise
    0.20
    侥幸
    0.20
     rate
    0.20
     ventil
    0.19
    .BLL
    0.19
    Activations Density 0.129%

    No Known Activations