© 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. 24132
    Prev
    Next
    INDEX
    Explanations

    ws. or ws connection

    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
    [Math
    -0.09
    ढ
    -0.09
    çĵľ
    -0.09
    refs
    -0.08
    丢
    -0.08
    èĻı
    -0.08
    å¾ĹçĽĬ
    -0.08
    黧
    -0.08
    åģ¥èº«æĪ¿
    -0.08
    à¹Ĥย
    -0.08
    POSITIVE LOGITS
     ÐIJвÑĤоÑĢ
    0.10
    æ§Ľ
    0.09
     Abyss
    0.09
    社ä¼ļ责任
    0.09
    åģıåģı
    0.09
    è¿Ļä¹Īåģļ
    0.09
    iston
    0.09
    æŀŃ
    0.08
    aly
    0.08
    Ñģло
    0.08
    Activations Density 0.039%

    No Known Activations