© 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. 26337
    Prev
    Next
    INDEX
    Explanations

    sports and competitions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĪ
    -0.09
    ard
    -0.08
     Dir
    -0.08
    æĹĮ
    -0.08
    鸩
    -0.08
    amma
    -0.08
     lle
    -0.07
    unity
    -0.07
    ä½İä¸ĭ
    -0.07
    town
    -0.07
    POSITIVE LOGITS
    æij©æīĺ车
    0.10
    ç²ĺ
    0.10
    è±ĨæµĨ
    0.10
    æľ¬åĽ½
    0.10
     tennis
    0.10
    è·ijæŃ¥
    0.10
    顶å°ĸ
    0.10
    åİķ
    0.09
     Gol
    0.09
    æīĺç¦ı
    0.09
    Activations Density 0.241%

    No Known Activations