© 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. 63907
    Prev
    Next
    INDEX
    Explanations

    before opening, before submitted, beforeTextChanged

    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
    黳
    -0.09
     Lans
    -0.09
    ä¸įæŃ¢
    -0.09
    ä¸įæĢķ
    -0.08
    ä½łçİ°åľ¨
    -0.08
    èĢĮä¸į
    -0.08
    没éĶĻ
    -0.08
    æŃ£åľ¨
    -0.08
    REW
    -0.08
     zwar
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.12
    (before
    0.11
    çļĦå®ŀéĻħ
    0.11
     anymore
    0.10
    å®ŀéĻħ
    0.10
    ä»»ä½ķ人
    0.10
    æŃ£å¼ı
    0.10
    å½»åºķ
    0.09
     ÙĪبعد
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    Activations Density 0.165%

    No Known Activations