© 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. 38913
    Prev
    Next
    INDEX
    Explanations

    Korean technology development

    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
    ahu
    -0.09
    åĵĢ
    -0.08
     دÙħØ´
    -0.08
    æľķ
    -0.08
    ãĥıãĤ¦
    -0.07
    æĸ¹åı¯
    -0.07
    áĥ¥
    -0.07
    ãĤ·ãĤ¹ãĥĨ
    -0.07
    çłģ头
    -0.07
    礼è²Į
    -0.07
    POSITIVE LOGITS
    æĺ¯éŁ©åĽ½
    0.22
    éŁ©åĽ½
    0.20
     Korea
    0.20
     Seoul
    0.18
     Korean
    0.18
     Koreans
    0.17
    æľĿé²ľ
    0.16
    飩
    0.16
    cheon
    0.15
    éŁĵ
    0.12
    Activations Density 0.820%

    No Known Activations