© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2911
    Prev
    Next
    INDEX
    Explanations

    exclamations followed by words

    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
    åıijåħī
    -0.10
    tır
    -0.09
    èIJ¥åķĨ
    -0.09
    å¼ĢåѦ
    -0.09
    Await
    -0.09
    èĩ³æĸ¼
    -0.09
    åľ¨ä¸Ĭæµ·
    -0.09
    tÃł
    -0.09
     Vince
    -0.09
    ?action
    -0.09
    POSITIVE LOGITS
    ç«ŁçĦ¶
    0.11
    ç«Ł
    0.10
    æĦıå¤ĸ
    0.10
    éĤ£ä¹Īå¤ļ
    0.09
    æĢİä¹Īèĥ½
    0.09
    滥
    0.09
    åIJ¬å®Į
    0.09
    æĢİä¹Īä¼ļ
    0.09
    éģį
    0.09
    addr
    0.09
    Activations Density 0.061%

    No Known Activations