© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37800
    Prev
    Next
    INDEX
    Explanations

    one, other, second

    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
    ç«£
    -0.10
    ä¸įèĥ½åĨį
    -0.09
    ä¼ŀ
    -0.09
    æ¬łç¼º
    -0.09
    éĥ½è§īå¾Ĺ
    -0.09
    èĤīç±»
    -0.08
    ÑģÑĤи
    -0.08
    ä¸Ģè½®
    -0.08
    éĵ¶è¡Įä¸ļ
    -0.08
    æľĢåħĪ
    -0.08
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹Īåij¢
    0.13
    åĪĻæĺ¯
    0.12
    æĺ¯åľ¨
    0.10
    æĺ¯ä¸ŃåĽ½
    0.10
    æĺ¯å¯¹
    0.09
    æĺ¯æĮĩ
    0.09
    为æ°ij
    0.09
    便æĺ¯
    0.09
    ä¸Ģ个æĺ¯
    0.09
    å°±æĺ¯
    0.08
    Activations Density 0.087%

    No Known Activations