© 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. 36524
    Prev
    Next
    INDEX
    Explanations

    lace or aced

    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
    ä¼ļéķ¿
    -0.11
    orce
    -0.09
    zed
    -0.09
    ãģĦãģŁãĤī
    -0.09
    æľīèī²éĩijå±ŀ
    -0.09
    à¸ij
    -0.09
    æ¦Ķ
    -0.09
    à¨Ĩ
    -0.09
     sÃłng
    -0.09
     stripslashes
    -0.09
    POSITIVE LOGITS
    less
    0.12
    ../../../
    0.12
    lessly
    0.12
    LESS
    0.10
    lette
    0.09
    оÑĩек
    0.09
    wares
    0.09
    WISE
    0.09
    ãģĮãĤī
    0.09
    pire
    0.09
    Activations Density 0.017%

    No Known Activations