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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7946
    Prev
    Next
    INDEX
    Explanations

    company name and address

    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
    .Expect
    -0.09
    æĻ¯åĮº
    -0.08
     overs
    -0.08
    æĦļ
    -0.08
    诬
    -0.08
     Gül
    -0.08
    æµĭ
    -0.08
    רת
    -0.08
    ignon
    -0.08
     skl
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥èĮĥåĽ´
    0.11
    éĽĩ
    0.10
    pto
    0.09
    æ³ķå®ļ代表
    0.09
    ç»ıèIJ¥æ¨¡å¼ı
    0.09
    èµĦè´¨
    0.08
    å½¹
    0.08
     vulner
    0.08
    åĸĺ
    0.08
    主èIJ¥
    0.08
    Activations Density 0.052%

    No Known Activations