© 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. 63229
    Prev
    Next
    INDEX
    Explanations

    professional-looking

    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
    Classic
    -0.11
     Classic
    -0.10
    èºģ
    -0.08
    å²Ń
    -0.08
    åıªåī©ä¸ĭ
    -0.08
    庶
    -0.08
    身åŃIJ
    -0.08
    äºĭåĦ¿
    -0.08
    Gam
    -0.08
    бо
    -0.08
    POSITIVE LOGITS
    ä¸ĵä¸ļ人士
    0.13
     professional
    0.11
    ä¸ĵä¸ļ
    0.11
    é«ĺè´¨éĩı
    0.11
    大çīĩ
    0.11
    æ°´åĩĨ
    0.10
    æŃ£å¼ı
    0.10
    é«ĺæĺĤ
    0.10
     professionally
    0.10
    æĺĤè´µ
    0.10
    Activations Density 0.101%

    No Known Activations