© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    workshop and workshops

    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
    æĸ°å¼Ģ
    -0.10
    å¼ĢéĢļ
    -0.09
    æł¡å¤ĸ
    -0.08
    åıijæĸĩ
    -0.08
    å¤ļä½ĻçļĦ
    -0.08
    ham
    -0.08
    eno
    -0.08
     mort
    -0.08
    mere
    -0.07
    å¤ļä½Ļ
    -0.07
    POSITIVE LOGITS
    æ´»æĢ§
    0.10
    æ´»è·ĥ
    0.10
     workshops
    0.10
    æĿ¥ä¸įåıĬ
    0.10
    ç»ĥä¹ł
    0.10
     workshop
    0.09
    笥
    0.09
    ãĥ¯ãĥ¼ãĤ¯
    0.09
    å°ıç»Ħ
    0.09
    æ´»åĬ¨ä¸Ń
    0.09
    Activations Density 0.059%

    No Known Activations