© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51380
    Prev
    Next
    INDEX
    Explanations

    Australian rules football

    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
    ç«ĸ
    -0.09
     Tong
    -0.09
     esp
    -0.09
    5
    -0.08
     fond
    -0.08
    6
    -0.08
     Kitt
    -0.08
    à¹Ĥà¸Ļ
    -0.08
    3
    -0.08
    å¥ij
    -0.08
    POSITIVE LOGITS
    æĹłèģĬ
    0.10
    æĢ»éĥ¨
    0.10
    大éŨ
    0.09
    wcs
    0.09
    好æĦŁ
    0.09
    ä¸įæĪIJ
    0.09
    uale
    0.09
    ija
    0.09
    æŃ£éĿ¢
    0.09
    ç¦ĭ
    0.09
    Activations Density 0.293%

    No Known Activations