© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19394
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    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
    åįĸç»Ļ
    -0.09
    ä¸ĢéŨ
    -0.09
     bulk
    -0.08
    RTOS
    -0.08
    bulk
    -0.08
    ä¸ŃåĽ½æĶ¿åºľ
    -0.08
    airo
    -0.08
    èIJ½åĪ°
    -0.08
    -tm
    -0.08
    глаÑģ
    -0.08
    POSITIVE LOGITS
    ä¸ĢåIJ¬
    0.09
    ä¸¤åľ°
    0.09
    æľĢ大çļĦ
    0.09
    åħĨ
    0.09
    å¾Īå¿«
    0.08
    å·¡åĽŀ
    0.08
     audiences
    0.08
    iesel
    0.08
    ä¹ĥèĩ³
    0.08
    urve
    0.08
    Activations Density 0.102%

    No Known Activations