© 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. 61958
    Prev
    Next
    INDEX
    Explanations

    elderly, disabled, sick, or dying people

    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
    åıĪ好
    -0.10
    æijĬ
    -0.09
    chrift
    -0.09
     ÑģÑĤо
    -0.09
    åIJĦæł·
    -0.09
    jos
    -0.09
    éºĵ
    -0.09
    åħģ
    -0.09
    çıŃ
    -0.09
    arf
    -0.09
    POSITIVE LOGITS
    æĹłåĬ©
    0.11
     Ill
    0.09
    å¼±åĬ¿
    0.09
    æ®ĭçĸ¾äºº
    0.09
     elderly
    0.09
     ill
    0.09
     who
    0.09
     disabled
    0.08
    强èĢħ
    0.08
     sick
    0.08
    Activations Density 0.078%

    No Known Activations