© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10189
    Prev
    Next
    INDEX
    Explanations

    basketball tournament

    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
    ç¢ĵ
    -0.12
    åѤ
    -0.11
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    缺å¸Ń
    -0.09
    sdale
    -0.09
    å¼ĢæĪ·
    -0.09
    è¹Ī
    -0.09
    æĪijçĪ±ä½ł
    -0.09
    æľī大éĩıçļĦ
    -0.09
    é¾Ł
    -0.09
    POSITIVE LOGITS
    Hold
    0.10
     NBA
    0.10
     basketball
    0.09
     Crane
    0.09
    lish
    0.09
    DET
    0.08
    iled
    0.08
    æĮģæľī
    0.08
    ä¿Ĺè¯Ŀ说
    0.08
     Vill
    0.08
    Activations Density 0.130%

    No Known Activations