© 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. 56909
    Prev
    Next
    INDEX
    Explanations

    creating or accessing their

    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
    éĤ£äºº
    -0.13
    æĪIJ为ä¸ĢåIJį
    -0.13
    æĺ¯ä¸ĢåIJį
    -0.13
    æĪIJ为ä¸Ģ个
    -0.13
    ä¹Łæĺ¯ä¸Ģ个
    -0.12
    éĤ£ä¸ªäºº
    -0.12
    ä½ľä¸ºä¸ĢåIJį
    -0.12
    ä½ľä¸ºä¸Ģ个
    -0.12
    ä½łä¼ļ
    -0.11
    æŃ¤äºº
    -0.11
    POSITIVE LOGITS
     themselves
    0.39
    åIJĦèĩªçļĦ
    0.24
    åIJĦèĩª
    0.24
    ä»ĸ们çļĦ
    0.24
    ä½Ĩä»ĸ们
    0.20
    纷纷
    0.19
     Ñģами
    0.19
     thems
    0.18
    ä»ĸä»¬åľ¨
    0.18
     their
    0.17
    Activations Density 0.544%

    No Known Activations