© 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. 36497
    Prev
    Next
    INDEX
    Explanations

    Royal Institution of Chartered Surveyors

    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
     ÙĪجÙĩ
    -0.09
    飧
    -0.09
    .yahoo
    -0.09
    accordion
    -0.08
    ä¾Ħ
    -0.08
    å·¥ä¸ļåĽŃ
    -0.08
    æľīæĦı
    -0.08
    relude
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    润
    -0.08
    POSITIVE LOGITS
    æģŃ
    0.09
    椿
    0.09
    çŁ¿çī©
    0.09
    åĬŁçĶ¨
    0.08
    æİĸ
    0.08
    常年
    0.08
    å¤ļä½ĻçļĦ
    0.08
    ä¸įèĥ½åĨį
    0.08
    Sending
    0.08
     Surrey
    0.08
    Activations Density 0.058%

    No Known Activations