© 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. 19628
    Prev
    Next
    INDEX
    Explanations

    class president prefect student grades

    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
    ä¸įå®Į
    -0.11
    Church
    -0.10
    åł¤
    -0.09
    łĢ
    -0.09
    été
    -0.08
    éri
    -0.08
    è¦ģåѦä¼ļ
    -0.08
    åŃĢ
    -0.08
    çłĢ
    -0.08
    çīĮçħ§
    -0.08
    POSITIVE LOGITS
    ä¼ĺå¼Ĥ
    0.09
    ä¹Łä¸įæķ¢
    0.09
    ãĤ¦ãĥ³
    0.08
    .promise
    0.08
    åIJįåĪĹåīįèĮħ
    0.08
    ahn
    0.08
    家åºŃ
    0.08
    æķĻèĤ²èµĦæºIJ
    0.08
    è¿ĻåIJį
    0.08
    PIO
    0.08
    Activations Density 0.016%

    No Known Activations