© 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. 39810
    Prev
    Next
    INDEX
    Explanations

    China's government and business

    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
    对ä¸ŃåĽ½
    -0.10
    åĭ¤å¥ĭ
    -0.10
    åįİ人
    -0.09
    ä¸ŃåĽ½éĺŁ
    -0.09
    å¼ĢåIJ¯äºĨ
    -0.09
    为ä¸ŃåĽ½
    -0.09
    å¤ĩ
    -0.09
    åįĶåĬ©
    -0.09
    åį§
    -0.09
    为大家
    -0.09
    POSITIVE LOGITS
    омеÑĢ
    0.10
    åįģä¸īäºĶ
    0.10
    GPL
    0.10
    é«ĺ端
    0.10
    ACHI
    0.09
    å¢ŀéĩı
    0.09
    -Allow
    0.09
    ä¸ĵä¸ļåĮĸ
    0.08
    åİ»è¿ĩ
    0.08
    ç¨İè´¹
    0.08
    Activations Density 0.218%

    No Known Activations