© 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. 26164
    Prev
    Next
    INDEX
    Explanations

    nationalist independence liberation movements

    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
    izen
    -0.11
    æµģç¨ĭ
    -0.10
    æŬ
    -0.09
    ä¹IJ趣
    -0.09
    äºīè®®
    -0.08
    æű
    -0.08
    åĭ¾
    -0.08
     обо
    -0.08
    åģ¥
    -0.08
    çĻ½å®«
    -0.08
    POSITIVE LOGITS
     independence
    0.11
    åıįæĬĹ
    0.10
    主æĿĥ
    0.10
     Independence
    0.10
    uala
    0.10
    çĭ¬ç«ĭ
    0.10
    æ®ĸæ°ij
    0.10
    鬥
    0.10
    æīĺ管
    0.10
    çį¨ç«ĭ
    0.10
    Activations Density 0.097%

    No Known Activations