© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2203
    Prev
    Next
    INDEX
    Explanations

    trade policy

    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
    ieten
    -0.09
    æĮª
    -0.09
    轩è¾ķ
    -0.08
    çŀ
    -0.08
    åĨįä¸Ģ次
    -0.08
    ÑĢеÑģ
    -0.08
    UTILITY
    -0.08
    éĺ¿æĭī伯
    -0.08
    çļĦ带é¢Ĩ
    -0.08
    èħ°éĥ¨
    -0.08
    POSITIVE LOGITS
    tem
    0.10
     اÙĦتجارة
    0.10
    ä¸ĸè´¸
    0.09
    èµŃ
    0.09
    оваÑĢ
    0.09
    æĭ±
    0.09
    çłĿ
    0.09
    éĵľ
    0.09
    è´¸æĺĵ
    0.09
    åĩĨåħ¥
    0.09
    Activations Density 0.060%

    No Known Activations