© 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. 55939
    Prev
    Next
    INDEX
    Explanations

    is/was adjective

    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
    é«Ģ
    -0.11
    çļĦæĢ§æł¼
    -0.10
    çijģ
    -0.10
    DataAdapter
    -0.10
    dden
    -0.09
    çļĦçĶŁæ´»
    -0.09
    æĻ¯è±¡
    -0.09
    ç½ij讯
    -0.09
    anium
    -0.09
    ä¸įå°ı
    -0.09
    POSITIVE LOGITS
    åĪ°ä½į
    0.13
    è¿Ļæĸ¹éĿ¢
    0.09
    ä¸įåĪ°ä½į
    0.09
    åĬŁ
    0.09
    åľ¨ä¸Ģ
    0.08
    _aspect
    0.08
    .descriptor
    0.08
    æ§ģ
    0.08
     haus
    0.08
    æīįæĺ¯
    0.08
    Activations Density 0.056%

    No Known Activations