© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9616
    Prev
    Next
    INDEX
    Explanations

    participant in a system

    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
    æĪij们ä¸Ģèµ·
    -0.11
    ä»ĸ说
    -0.10
    æĪij说
    -0.09
    èĵ¼
    -0.09
    å½ĵä½ł
    -0.09
    æĪij们就
    -0.09
    大家
    -0.09
     denen
    -0.09
    ÃŃv
    -0.08
     bottoms
    -0.08
    POSITIVE LOGITS
    éĢŀ
    0.09
    èĥŃ
    0.09
    ä¼¢
    0.09
    å±ĤéĿ¢
    0.09
    亲
    0.09
     اÙĦÙħسÙĦÙħ
    0.08
    ãģ»ãģĨ
    0.08
    è¯Ńæĸĩ
    0.08
    è¿Ļè¾¹
    0.08
    亲èĩª
    0.08
    Activations Density 0.120%

    No Known Activations