© 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. 9116
    Prev
    Next
    INDEX
    Explanations

    protocols and standards

    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
    æ¥ł
    -0.10
    åij¨è½¬
    -0.09
    è¿Ļ件
    -0.09
    åĬ¬
    -0.09
    ä¹ĸä¹ĸ
    -0.09
    /from
    -0.09
    é¹Ĥ
    -0.09
    äºĨèµ·æĿ¥
    -0.08
    æĪIJéķ¿ä¸º
    -0.08
    åIJĦæł·
    -0.08
    POSITIVE LOGITS
    ä¸ŃæľĢ
    0.10
    åħ³äºİ
    0.09
    ä¸Ńæľī
    0.09
     ÑĤипа
    0.08
    ‘
    0.08
    çļĨ
    0.08
    emet
    0.08
    uction
    0.08
    tá
    0.08
     ‘
    0.08
    Activations Density 0.491%

    No Known Activations