© 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. 21000
    Prev
    Next
    INDEX
    Explanations

    craftsmanship and artisans

    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
    å¼Ĭ
    -0.09
    uffer
    -0.09
    æķŀ
    -0.09
    ç§ķ
    -0.09
    å¼ĢéĢļ
    -0.09
    忧
    -0.09
    é¢ĦèѦ
    -0.08
     pioneers
    -0.08
    ä¸įå®Į
    -0.08
    éĿ¢çĽ®
    -0.08
    POSITIVE LOGITS
    å·¥åĮł
    0.20
    æĬĢèīº
    0.19
    åĮł
    0.19
    æīĭèīº
    0.17
    å·¥èīº
    0.17
    å¸ĪåĤħ
    0.17
    å·¥åºı
    0.16
    æīĭå·¥
    0.16
     маÑģÑĤ
    0.15
     craftsmanship
    0.15
    Activations Density 0.123%

    No Known Activations