© 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. 52259
    Prev
    Next
    INDEX
    Explanations

    banh mi, bread, cake, Danish

    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
    hem
    -0.09
    æ·¡æ·¡çļĦ
    -0.09
    è¹Ī
    -0.09
    天ä¸Ĭ
    -0.08
    æ³Ĺ
    -0.08
     Mour
    -0.08
    ÑĪки
    -0.08
    ä½ĵä¼ļåĪ°
    -0.08
    vidence
    -0.08
    åįī
    -0.08
    POSITIVE LOGITS
    ä»°
    0.09
    嫦
    0.09
    è½½ä½ĵ
    0.09
    ersions
    0.09
    æľīèĥ½åĬĽ
    0.08
    ervals
    0.08
     Daily
    0.08
    çŃı
    0.08
     Whale
    0.08
    åł±
    0.08
    Activations Density 0.002%

    No Known Activations