© 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. 30160
    Prev
    Next
    INDEX
    Explanations

    Greek history and geography

    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
    å¯Ŀ室
    -0.09
    åī¿
    -0.09
    æĺ¥å¤ı
    -0.08
    èģĶ缣
    -0.08
    ç½®
    -0.08
    为ä¹ĭ
    -0.08
    åħģ
    -0.08
     اÙĦÙħÙħÙĦ
    -0.08
    åķIJ
    -0.08
    argon
    -0.08
    POSITIVE LOGITS
    å¸ĮèħĬ
    0.15
     Greek
    0.13
     Greeks
    0.12
     Greece
    0.12
     Cyprus
    0.11
    Τ
    0.11
    Greek
    0.11
     그리ìĬ¤
    0.10
     Balk
    0.09
    Îľ
    0.09
    Activations Density 0.156%

    No Known Activations