© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36869
    Prev
    Next
    INDEX
    Explanations

    machine learning

    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
    stad
    -0.10
    æģ¢
    -0.10
    建çŃij设计
    -0.09
     Pars
    -0.09
    ãģ¨ãģĨ
    -0.09
     thiếu
    -0.09
     distr
    -0.08
    å³Ĵ
    -0.08
    ãĥĭãĥ¼
    -0.08
    å»ī
    -0.08
    POSITIVE LOGITS
     learning
    0.13
    åŃ¦ä¹ł
    0.13
    çļĦåŃ¦ä¹ł
    0.10
    åѸç¿Ĵ
    0.10
    learning
    0.10
     Learning
    0.10
     learn
    0.09
    .learning
    0.09
     bitter
    0.09
    -learning
    0.09
    Activations Density 0.075%

    No Known Activations