© 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. 750
    Prev
    Next
    INDEX
    Explanations

    Russian names and locations

    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
    acre
    -0.10
    æģ¯
    -0.09
    åĺ´
    -0.09
    åı£
    -0.09
    éĥ¨èIJ½
    -0.09
    è¹²
    -0.08
    åĺ´å·´
    -0.08
    æĽ·
    -0.08
     crack
    -0.08
    æķ¬ä¸ļ
    -0.08
    POSITIVE LOGITS
    ä¿Ħç½Ĺæĸ¯
    0.20
    èİ«æĸ¯ç§ij
    0.19
     Russian
    0.18
     Russians
    0.17
    ä¿ĦåĽ½
    0.17
     russian
    0.17
    Russia
    0.17
     Russia
    0.17
    Russian
    0.16
    ä¿ĦåĨĽ
    0.16
    Activations Density 0.380%

    No Known Activations