© 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. 8393
    Prev
    Next
    INDEX
    Explanations

    relative clauses with which

    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
    æĢ§å¼º
    -0.11
    说æĪij
    -0.10
    çļĦå°±æĺ¯
    -0.10
    çľĭä½ł
    -0.10
    å°±æĺ¯è¦ģ
    -0.10
    è¿Ļä¸įæĺ¯
    -0.09
    èµĽåĮº
    -0.09
    åĿı
    -0.09
    群
    -0.09
    ä»Ģä¹Īåij¢
    -0.08
    POSITIVE LOGITS
    涨
    0.10
    .Serializable
    0.09
    atee
    0.09
    æľĢç»Ī
    0.08
    spiel
    0.08
    æĪIJ为äºĨ
    0.08
    grown
    0.08
    iales
    0.08
    ä¸¥æł¼
    0.08
    ä¹Łæĺ¯ä¸Ģ个
    0.08
    Activations Density 0.157%

    No Known Activations