© 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. 4694
    Prev
    Next
    INDEX
    Explanations

    same followed by noun

    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
    离
    -0.09
    轻微
    -0.09
    æį·
    -0.09
    è¿Ļç§įæĸ¹å¼ı
    -0.09
    åĩ¡æĺ¯
    -0.09
    饶
    -0.09
    åĽ½ä¼ģ
    -0.09
     ÐĹна
    -0.08
    äºĨ好åĩł
    -0.08
    è¿ŀè¿ŀ
    -0.08
    POSITIVE LOGITS
    åIJĮä¸Ģ
    0.18
    åľ¨åIJĮä¸Ģ
    0.16
    åIJĮä¸Ģ个
    0.15
    åIJĮãģĺ
    0.14
     same
    0.14
    åIJĮæł·çļĦ
    0.14
    缸åIJĮçļĦ
    0.13
    same
    0.12
     mesma
    0.11
     misma
    0.11
    Activations Density 0.125%

    No Known Activations