© 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. 55001
    Prev
    Next
    INDEX
    Explanations

    modern society and abstract concepts

    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
    ä¹Łæľīä¸ĢäºĽ
    -0.09
    çľģå§Ķ
    -0.09
    äºĭåIJİ
    -0.09
    并ä¸įä¼ļ
    -0.09
    ä¹Łæľīå¾Īå¤ļ
    -0.09
    åĸ
    -0.09
    æ¯ķç«Łæĺ¯
    -0.09
    åıĹå½±åĵį
    -0.09
    èĢģ乡
    -0.08
    å°±æĺ¯è¦ģ
    -0.08
    POSITIVE LOGITS
    娱ä¹IJ
    0.11
    æĸ¤
    0.10
    è¶ĬæĿ¥è¶Ĭ
    0.10
    å¿«é¤IJ
    0.10
    åıĸ代
    0.10
    è¿ŀ
    0.10
    æĢ¥
    0.09
     ÑĤеле
    0.09
     entertainment
    0.09
     increasingly
    0.09
    Activations Density 0.085%

    No Known Activations