© 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. 29509
    Prev
    Next
    INDEX
    Explanations

    green energy technologies and hydrogen

    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
    Negative Logits
    å·¥å§Ķ
    -0.10
     bes
    -0.10
    丰
    -0.10
    åĩĮæĻ¨
    -0.09
    æĭľ
    -0.09
    bes
    -0.09
    踵
    -0.09
    说æľį
    -0.08
     kê
    -0.08
    itta
    -0.08
    POSITIVE LOGITS
    æ¸ħæ´ģ
    0.14
     clean
    0.11
     cleaner
    0.10
    æ´ģåĩĢ
    0.10
    clean
    0.10
     CLEAN
    0.09
    æ´ģ
    0.09
    èݺ
    0.09
     Clean
    0.09
    è¿ĩ渡
    0.08
    Activations Density 0.079%

    No Known Activations