© 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. 20532
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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¸Ńå¼ı
    -0.09
    è¿Ļä¸Ģ天
    -0.09
    æ£ł
    -0.09
    éĤ£ä¸ĢåĪ»
    -0.09
    æĬĬæı¡
    -0.08
    æ·¹
    -0.08
    éĤ£ä¸Ģ天
    -0.08
     Bernardino
    -0.08
    ê³°
    -0.08
    åijĬ
    -0.08
    POSITIVE LOGITS
    ä¸ĢæŃ¥
    0.11
    üss
    0.09
    ä¸Ģè¡Į
    0.09
    ä¸ĢçĤ¹åĦ¿
    0.09
    ä¸ĢåĪĢ
    0.09
    _PIXEL
    0.09
    å°º
    0.08
    尺度
    0.08
    ä¸ĢäºĮ
    0.08
     gravid
    0.08
    Activations Density 0.217%

    No Known Activations