© 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. 2410
    Prev
    Next
    INDEX
    Explanations

    Korean and Chinese surnames

    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
    аÑĢам
    -0.09
    åįģåĽĽäºĶ
    -0.09
    åĽŃ
    -0.09
    å°ģ
    -0.09
    ä¹ŁæŃ£æĺ¯
    -0.09
    é¹ħ
    -0.08
     synagogue
    -0.08
    ç¼Ħ
    -0.08
    éķĤ
    -0.08
    ç³Ļ
    -0.08
    POSITIVE LOGITS
    æ°ı
    0.11
    å³Ļ
    0.09
    wel
    0.08
    åĤ¢
    0.08
    æĥľ
    0.08
    æ¡ģ
    0.08
    ä»İåīį
    0.08
    åįĥéĩĮ
    0.08
    åħĨ
    0.08
    æĨ
    0.08
    Activations Density 0.075%

    No Known Activations