© 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. 54141
    Prev
    Next
    INDEX
    Explanations

    trade policy and international business

    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
    å©ļ
    -0.09
    ehr
    -0.09
    èģĺ
    -0.08
    åIJij社ä¼ļ
    -0.08
     ow
    -0.08
    æĻ´
    -0.08
    西åįĹ
    -0.08
     Ow
    -0.08
    人身
    -0.08
    eps
    -0.07
    POSITIVE LOGITS
    éĢļåħ³
    0.15
    è´¸æĺĵ
    0.14
    å¤ĸè´¸
    0.14
    åĽ½éĻħè´¸æĺĵ
    0.12
    è·¨å¢ĥçĶµåķĨ
    0.12
    ç«ŀäºīä¼ĺåĬ¿
    0.12
    èĩªçĶ±è´¸æĺĵ
    0.12
     WTO
    0.11
    è´§çī©
    0.11
    åĩºåı£
    0.11
    Activations Density 0.096%

    No Known Activations