© 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. 23433
    Prev
    Next
    INDEX
    Explanations

    surprise or unexpected

    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
    lesh
    -0.10
    èĪī
    -0.09
    妹妹
    -0.09
    åѤç«ĭ
    -0.09
    è¯įè¯Ń
    -0.09
    å¼Ł
    -0.09
    éģĩä¸Ĭ
    -0.09
    ä½ĵä¼ļ
    -0.09
    enz
    -0.09
    举
    -0.09
    POSITIVE LOGITS
    å±ħçĦ¶
    0.17
    ç«ŁçĦ¶
    0.17
    æĦıæĥ³ä¸įåĪ°
    0.16
    ç«Łæĺ¯
    0.15
     surprising
    0.15
    ç«Ł
    0.14
     unexpected
    0.14
    æĦıå¤ĸ
    0.14
     surprisingly
    0.13
    unexpected
    0.12
    Activations Density 0.074%

    No Known Activations