© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22919
    Prev
    Next
    INDEX
    Explanations

    ancient civilizations and eras

    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
    紧迫
    -0.10
     Atkins
    -0.10
    è¦ģåģļ好
    -0.09
    åĪ»
    -0.09
    ä¸Ģåī¯
    -0.09
    æİ¥
    -0.09
    åĬŁ
    -0.09
     ÐľÐµ
    -0.09
    æĮĿ
    -0.09
    ãĤ¦ãĤ©ãĥ¼
    -0.09
    POSITIVE LOGITS
    åŀ®
    0.11
    缺
    0.10
    èĪľ
    0.09
    è¾Ļ
    0.09
    æľ¬è½®
    0.09
     Jonas
    0.09
    樽
    0.08
     Bruins
    0.08
    åħħåĪĨèĤ¯å®ļ
    0.08
     topLevel
    0.08
    Activations Density 0.061%

    No Known Activations