© 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. 26203
    Prev
    Next
    INDEX
    Explanations

    national organizations and institutions

    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
    lâ
    -0.10
    æŀ£
    -0.10
    åħ¬åı¸å°Ĩ
    -0.09
    å¿į
    -0.09
    åľ¨åĽ½å¤ĸ
    -0.09
    ä¸įçŁ¥
    -0.08
    礼åĮħ
    -0.08
    人ãģĮ
    -0.08
    å°ıå§IJå§IJ
    -0.08
    аÑĩ
    -0.08
    POSITIVE LOGITS
    æ¯įæł¡
    0.09
    ä½ľèĢħæľ¬äºº
    0.08
    åķ¾
    0.08
    ãĥļãĥĥãĥĪ
    0.08
    åŀ¸
    0.08
    _pet
    0.08
    .clips
    0.08
    塵
    0.07
    omin
    0.07
    åħ¨éķĩ
    0.07
    Activations Density 0.122%

    No Known Activations