© 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. 49813
    Prev
    Next
    INDEX
    Explanations

    questioning auxiliary verbs

    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
    æĸĩåĮĸ产ä¸ļ
    -0.09
    å¾Īä¹ħ
    -0.09
    æĮĿ
    -0.08
     either
    -0.08
    åĨįä¹Łæ²¡æľī
    -0.08
    ÑģÑħод
    -0.08
    å¾Īå¤ļæŶåĢĻ
    -0.08
    éĻ¤éĿŀ
    -0.08
    ISA
    -0.08
     Lab
    -0.08
    POSITIVE LOGITS
    åij¢
    0.15
    ä»Ģä¹Īåij¢
    0.13
    æĺ¯ä»Ģä¹Īåij¢
    0.13
    è¿Ļå°±
    0.10
    æ³¥
    0.09
    å¨ģ
    0.09
     ÑĥвелиÑĩи
    0.09
    éĺŁåijĺ们
    0.09
    èĥª
    0.09
     же
    0.09
    Activations Density 0.074%

    No Known Activations