© 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. 27984
    Prev
    Next
    INDEX
    Explanations

    economic development and incentives

    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
    æĻ®åıĬ
    -0.11
    澳大
    -0.10
    大ä¼Ĺ
    -0.10
    æĻĸ
    -0.10
    æĢĻ
    -0.10
    汶å·Ŀ
    -0.09
    å¸ı
    -0.09
    西æ´ĭ
    -0.09
    æ·Ĩ
    -0.09
    ienne
    -0.09
    POSITIVE LOGITS
    æĭĽåķĨå¼ķèµĦ
    0.21
    æĭĽåķĨ
    0.17
    åIJ¸å¼ķ
    0.16
    æĭĽåķĨå¼ķ
    0.15
    åIJ¸å¼ķæĽ´å¤ļ
    0.14
    åIJ¸å¼ķåĬĽ
    0.14
     attract
    0.14
     attracting
    0.13
     attraction
    0.13
    åIJ¸å¼ķäºĨ
    0.12
    Activations Density 0.065%

    No Known Activations