© 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. 33057
    Prev
    Next
    INDEX
    Explanations

    human concepts loss 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
    åĵĦ
    -0.11
    æĢİä¹Ī说
    -0.11
     اÙĦØ°
    -0.10
    æł¼æŀĹ
    -0.10
     mãi
    -0.09
    çIJĨæĥ³çļĦ
    -0.09
    æĢª
    -0.09
    ä¹ĭåĬ¿
    -0.09
    arium
    -0.09
     اÙĦØŃاÙĦ
    -0.09
    POSITIVE LOGITS
    人æĢ§
    0.13
     human
    0.10
    æĻ®éĢļ人
    0.10
    -human
    0.10
    身åIJİ
    0.09
     Vulner
    0.09
    失误
    0.09
    çĥŁçģ«
    0.09
    æĥ§
    0.09
    cao
    0.08
    Activations Density 0.051%

    No Known Activations