© 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. 9065
    Prev
    Next
    INDEX
    Explanations

    football leagues and clubs

    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
    åIJĦåĽ½
    -0.10
    ä¸¤åĽ½
    -0.09
     countries
    -0.09
    äºı
    -0.09
    ä¸Ńç¾İ
    -0.09
    avl
    -0.09
    ogh
    -0.09
     Clarkson
    -0.09
    ä¸ĩåħ¬éĩĮ
    -0.09
    åķĥ
    -0.09
    POSITIVE LOGITS
    å°ıå¾®
    0.10
    å°ıå¾®ä¼ģä¸ļ
    0.09
    åħ¨åİ¿
    0.09
    à¸Ńà¸ļ
    0.09
     Ray
    0.09
    2
    0.08
    nil
    0.08
    County
    0.08
    çŀ»
    0.08
    -nil
    0.08
    Activations Density 0.309%

    No Known Activations