© 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. 9448
    Prev
    Next
    INDEX
    Explanations

    health care coverage financing

    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¿ĺåı¯
    -0.09
    æīĢåľ¨
    -0.09
    æīĢåľ¨çļĦ
    -0.09
    è¾ĥ大çļĦ
    -0.09
    é»Ħæĺı
    -0.08
    社ä¼ļ责任
    -0.08
    éķ¿çĽ¸
    -0.08
    ä»ĵ
    -0.08
    ä¼ģä¸ļæĸĩåĮĸ
    -0.08
    ä¸įæĸŃåľ°
    -0.08
    POSITIVE LOGITS
    rophy
    0.10
    è¿Ļ项
    0.09
    èĴ´
    0.09
    ÑģÑĤо
    0.09
    ç¾ŀ
    0.09
    insky
    0.08
    ÇĶ
    0.08
    Psi
    0.08
    è¦
    0.08
     Alv
    0.08
    Activations Density 0.018%

    No Known Activations