© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20751
    Prev
    Next
    INDEX
    Explanations

    standard of duty

    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
    æļĤ
    -0.09
    à¹ģà¸ģ
    -0.08
    dictionary
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    衽
    -0.08
    æĬ¥åIJį
    -0.08
    è´¿
    -0.08
     privat
    -0.08
     confront
    -0.08
    å¹´ç»Ī
    -0.08
    POSITIVE LOGITS
    åĩĨåĪĻ
    0.11
    楼
    0.11
    å·¡
    0.11
    尺度
    0.10
    çŁ¥è¯ĨçĤ¹
    0.10
    æ¨ĵ
    0.10
    ç¡®ç«ĭ
    0.10
    åĩĨ
    0.10
    審
    0.09
    ä¸Ģè·¯ä¸Ĭ
    0.09
    Activations Density 0.051%

    No Known Activations