© 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. 48213
    Prev
    Next
    INDEX
    Explanations

    Drag Race, pipes, Glasgow College

    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
     Câm
    -0.09
    åıij声
    -0.09
    éħįæľī
    -0.08
    æ²īæµ¸åľ¨
    -0.08
     appe
    -0.08
    çļĦçħ§çīĩ
    -0.08
    家ä½ı
    -0.08
    맨
    -0.08
    ÙĤار
    -0.08
    æĿĪ
    -0.08
    POSITIVE LOGITS
    å¼ıçļĦ
    0.10
    溥
    0.09
    alem
    0.09
    oup
    0.08
    å¾Īå¤ļäºĭæĥħ
    0.08
    oked
    0.08
    åŀĭ
    0.08
    uries
    0.08
    bing
    0.08
    ENSE
    0.08
    Activations Density 0.173%

    No Known Activations