© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51755
    Prev
    Next
    INDEX
    Explanations

    Russian, Chinese, or Japanese text

    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§ģè¿ĩ
    -0.10
    æĸ¹å¼ıè¿Ľè¡Į
    -0.10
    -
    -0.09
    3
    -0.08
    ill
    -0.08
    æѤ类
    -0.08
    åı¯ä»¥èİ·å¾Ĺ
    -0.08
    4
    -0.08
    åIJ¬è¿ĩ
    -0.07
    0
    -0.07
    POSITIVE LOGITS
    æĦıæĢĿæĺ¯
    0.11
    ниÑĨа
    0.11
    ä¸ĢæĬ¹
    0.10
    骥
    0.10
    çļĦåĽŀçŃĶ
    0.10
    骧
    0.10
    æľīä½ķ
    0.10
    åĽŀå¤į
    0.09
    skins
    0.09
    åĽŀçŃĶ
    0.09
    Activations Density 0.024%

    No Known Activations