© 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. 57828
    Prev
    Next
    INDEX
    Explanations

    geopolitics and international relations

    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
    èĩªåįij
    -0.10
    æľį
    -0.09
    çıŃåŃIJ
    -0.09
    åıĮåıĮ
    -0.09
    æĬ«
    -0.09
    amba
    -0.09
    ä»İä¸ļ
    -0.08
    对å¤ĸ
    -0.08
    æµģåĬ¨æĢ§
    -0.08
    媲
    -0.08
    POSITIVE LOGITS
    è¿Ļ对
    0.10
    åĩºèµĦ
    0.10
    uzzi
    0.09
    ä¼Ĺ
    0.09
    ä»ĭåħ¥
    0.09
     Summers
    0.09
    æĶ¯æĮģ
    0.09
    åĬłå¤§å¯¹
    0.09
     ủng
    0.08
     вли
    0.08
    Activations Density 0.057%

    No Known Activations