© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36165
    Prev
    Next
    INDEX
    Explanations

    themselves and other people

    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
    æĪIJ为ä¸Ģ个
    -0.12
    æĪIJ为ä¸ĢåIJį
    -0.10
    ä½ľä¸ºä¸Ģ个
    -0.10
    æĺ¯ä¸Ģ项
    -0.09
    estone
    -0.09
    äºĨä¸įå°ij
    -0.09
    ymb
    -0.09
    æ¾¥
    -0.09
    å¾Īæľīåı¯èĥ½
    -0.09
    ä¸įå°ij
    -0.09
    POSITIVE LOGITS
     themselves
    0.19
    ä»ĸ们çļĦ
    0.13
     their
    0.12
    çļĦ人æĿ¥è¯´
    0.12
    ä½Ĩä»ĸ们
    0.11
     Ñģами
    0.11
    åĽłä¸ºä»ĸ们
    0.11
    their
    0.10
    åIJĦèĩª
    0.10
     are
    0.09
    Activations Density 0.419%

    No Known Activations