© 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. 50647
    Prev
    Next
    INDEX
    Explanations

    Olympic events and ceremonies

    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
    IVEN
    -0.09
    pane
    -0.08
    åĸī
    -0.08
    æĻı
    -0.08
    speaker
    -0.08
    irts
    -0.08
    åĩºåħ¥
    -0.08
    ç©¿æ¢Ń
    -0.08
    èĤĿ
    -0.08
    éħį
    -0.08
    POSITIVE LOGITS
    奥è¿IJä¼ļ
    0.15
     Olympic
    0.14
    è¿IJåĬ¨ä¼ļ
    0.13
     Olympics
    0.13
    奥è¿IJ
    0.11
    çģ«çĤ¬
    0.11
    åĨ¬å¥¥ä¼ļ
    0.11
    奥æŀĹåĮ¹åħĭ
    0.11
    æĿĸ
    0.10
     Games
    0.10
    Activations Density 0.132%

    No Known Activations