© 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. 64135
    Prev
    Next
    INDEX
    Explanations

    indigenized diversities

    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
    елÑĮ
    -0.08
    æ¯ıä¸Ģ次
    -0.08
    æ¯ı次éĥ½
    -0.08
     tie
    -0.08
    нÑı
    -0.08
    (cls
    -0.08
    릿
    -0.07
    olated
    -0.07
    fos
    -0.07
     ÑįкÑģ
    -0.07
    POSITIVE LOGITS
    æį
    0.10
    æ¶İ
    0.10
    ä¾¥
    0.10
    æŀģ
    0.09
    诽
    0.09
    é«ĵ
    0.09
    æĥ¬
    0.09
    海峡
    0.09
    ç»İ
    0.09
     обоÑĢ
    0.09
    Activations Density 0.159%

    No Known Activations