© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12444
    Prev
    Next
    INDEX
    Explanations

    Estonia and Estonian related terms

    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
    Negative Logits
    顺
    -0.11
    鸽
    -0.10
     Leone
    -0.09
    isco
    -0.09
    iego
    -0.09
    æģĤ
    -0.09
    ä¸ĢéĿ¢
    -0.09
    纶
    -0.09
    åħ
    -0.09
    好åIJĹ
    -0.09
    POSITIVE LOGITS
    ç»Ħç»ĩå¼Ģå±ķ
    0.09
     Estonia
    0.09
     Eston
    0.09
    ä¸į大
    0.08
    anja
    0.08
    eper
    0.08
    æĮ¯ãĤĬ
    0.08
    ENTS
    0.08
    ks
    0.08
    æĮij
    0.08
    Activations Density 0.074%

    No Known Activations