© 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. 37445
    Prev
    Next
    INDEX
    Explanations

    trading, markets, and financial terms

    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
    èĦ¸
    -0.11
    è´¯
    -0.09
    èįĨå·ŀ
    -0.09
    éĿ¢éĥ¨
    -0.09
    çļĦèĦ¸
    -0.09
    ļĮ
    -0.09
    èĩī
    -0.09
    anson
    -0.08
    èĦ¸éĥ¨
    -0.08
    åĵı
    -0.08
    POSITIVE LOGITS
    æľºæ¢°
    0.10
    åħ¥å¸Ĥ
    0.09
    åĢĻ
    0.09
    売
    0.09
    ppo
    0.09
    å¥Ĺ
    0.09
    赢家
    0.09
    çŃĸçķ¥
    0.09
    èĢķ
    0.09
    çļĦä¿¡å¿ĥ
    0.09
    Activations Density 0.087%

    No Known Activations