© 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. 31216
    Prev
    Next
    INDEX
    Explanations

    for a common object

    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
     Perc
    -0.09
    zion
    -0.09
    CHED
    -0.09
    áŀģ
    -0.09
    anders
    -0.09
    ä¸į论
    -0.08
    çħ
    -0.08
     ìŀĪìĸ´ìĦľ
    -0.08
    FAULT
    -0.08
    éĢ¼
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·ä¸Ģ个
    0.17
    è¿Ļä¹Ī大
    0.16
    è¿Ļä¹Ī
    0.15
    æ¯ķç«Łæĺ¯
    0.14
    åľ¨ä¸Ģ个
    0.14
    è¿Ļä¹Īå¤ļ
    0.12
    ä¸Ģ个å¤ļ
    0.11
    è¿Ļä¹Īå¤ļå¹´
    0.11
    éĤ£ä¹Īå¤ļ
    0.11
    åģĮ
    0.10
    Activations Density 0.142%

    No Known Activations