© 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. 62244
    Prev
    Next
    INDEX
    Explanations

    expediated, urgent, delivery, fast, early

    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
    è¿Łè¿Ł
    -0.11
     Affero
    -0.09
    èĮ«çĦ¶
    -0.09
    é¢ĺ主
    -0.09
    éĺ»ç¢į
    -0.08
    arms
    -0.08
    è¯Ŀ说
    -0.08
    çĴĥ
    -0.08
    夫
    -0.08
    ä¸Ģä¼ļ
    -0.08
    POSITIVE LOGITS
    缩çŁŃ
    0.12
    æį·
    0.12
    æĢ¥
    0.12
    /fast
    0.11
    æĬ¢åįł
    0.09
     urg
    0.09
    赶
    0.09
    eldon
    0.09
    紧迫
    0.09
    gressive
    0.08
    Activations Density 0.064%

    No Known Activations