© 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. 4943
    Prev
    Next
    INDEX
    Explanations

    Microsoft Office applications

    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
    éĶĻ
    -0.09
    庶
    -0.09
    ä¸įè´Ł
    -0.08
    hung
    -0.08
    湫
    -0.08
    åıĺæĢģ
    -0.08
    çıŃ级
    -0.08
    èĥ½åĬĽå¼º
    -0.08
    åijĬ
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
    POSITIVE LOGITS
    Excel
    0.12
     Excel
    0.10
    æ¡ĮéĿ¢
    0.10
    computer
    0.10
    åĬŀåħ¬
    0.10
    .office
    0.10
    .Excel
    0.09
    excel
    0.09
    ç³Ĭ
    0.09
    Microsoft
    0.09
    Activations Density 0.170%

    No Known Activations