© 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. 24171
    Prev
    Next
    INDEX
    Explanations

    pursuing dreams and satisfaction

    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
    æµ®åĬ¨
    -0.09
    æľīæľŁ
    -0.09
    èĩªåįij
    -0.09
    çļĦå¿ĥæĢģ
    -0.09
    æŁ¬
    -0.09
    åŃ¦ä¹łæĪIJ绩
    -0.08
    èĴ²
    -0.08
    ä¸İæŶ
    -0.08
    好åĿı
    -0.08
    .Protocol
    -0.08
    POSITIVE LOGITS
    ä¸į满æĦı
    0.09
    çªĿ
    0.09
    adow
    0.09
    åİĺ
    0.09
    mts
    0.08
    ãĤĦãĤĬ
    0.08
    ä»ķ
    0.08
    æķ´ä½ĵ
    0.08
    å¼Ģå±ķ
    0.08
    追寻
    0.08
    Activations Density 0.059%

    No Known Activations