© 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. 61990
    Prev
    Next
    INDEX
    Explanations

    viticulture and winemaking

    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
     Mari
    -0.08
    åIJ¬å®Į
    -0.08
    ä¹°ä¸ľè¥¿
    -0.08
     seal
    -0.08
    ä»Ĭ
    -0.08
    è·ŁçĿĢ
    -0.08
    è¿ĩåħ³
    -0.08
    ä¸įè¿ľ
    -0.08
    æ¶Īè´¹éľĢæ±Ĥ
    -0.08
     subt
    -0.08
    POSITIVE LOGITS
     ÑĢай
    0.11
    èij¡èIJĦ
    0.10
    ült
    0.10
    ç§ijæĬĢåĽŃ
    0.10
    еле
    0.09
    ä¾ı
    0.09
     Cartoon
    0.09
     Yapı
    0.09
     truyá»ģn
    0.09
    estring
    0.09
    Activations Density 0.042%

    No Known Activations