© 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. 17710
    Prev
    Next
    INDEX
    Explanations

    chinese words and phrases

    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
    ä»İå°ı
    -0.11
    åĨįåĬłä¸Ĭ
    -0.09
    æľĢæĸ°çļĦ
    -0.09
    æĺ¨æĻļ
    -0.09
    é¢Ħ订
    -0.09
    åĪļåĪļ
    -0.09
    嬷
    -0.09
     PROT
    -0.08
    æĺİæĹ¥
    -0.08
    ÑĩеÑĢ
    -0.08
    POSITIVE LOGITS
    èĩ³ä»Ĭ
    0.11
    éĤ£æ¬¡
    0.11
    åıijçĶŁåľ¨
    0.10
    è®°å¿Ĩ
    0.09
    è®°å¾Ĺ
    0.09
    è¿Ħä»Ĭ
    0.09
    æĪĺ绩
    0.09
    éĩİå¤ĸ
    0.09
    äºĭ件
    0.09
    æ°ijåĽ½
    0.08
    Activations Density 0.133%

    No Known Activations