© 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. 63003
    Prev
    Next
    INDEX
    Explanations

    do not edit, message, mistake

    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¸įèĥ½åĨį
    -0.12
    ä¸įå¾Ĺä¸į
    -0.11
    ä¸įåıĹ
    -0.11
    ä¸įéĶĻçļĦ
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.10
    ä¸įåı¯èĥ½
    -0.10
    ä¸įå°ıçļĦ
    -0.10
    ä¸įåĨį
    -0.09
    Ñī
    -0.09
    æł¹æį®ä¸įåIJĮ
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.18
    ä¹Łä¸įè¦ģ
    0.18
    åĽłä¸ºä½ł
    0.13
    ä»»ä½ķ
    0.13
    èĢĮæĺ¯
    0.12
    ä»»ä½ķå½¢å¼ı
    0.12
    unless
    0.12
     nor
    0.12
     anymore
    0.11
    ä»»ä½ķ人
    0.11
    Activations Density 0.078%

    No Known Activations