© 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. 564
    Prev
    Next
    INDEX
    Explanations

    only or just

    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
    OV
    -0.09
    ä¸įåľ¨ä¹İ
    -0.09
    igh
    -0.08
    еÑĨ
    -0.08
    大èĥĨ
    -0.08
    ocr
    -0.08
    è¿Ļæł·ä¸ĢæĿ¥
    -0.08
    er
    -0.08
    åĽŀäºĭ
    -0.07
    æīĵçł´
    -0.07
    POSITIVE LOGITS
    æĪijåıªæĺ¯
    0.12
    èĢĮæĺ¯
    0.11
    åıªæĺ¯
    0.11
    éļ»
    0.10
    åıªåī©ä¸ĭ
    0.10
    ÑĤоп
    0.09
    ç¶ļ
    0.09
    åıªä¼ļ
    0.09
     merely
    0.09
    EIF
    0.09
    Activations Density 0.044%

    No Known Activations