© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52088
    Prev
    Next
    INDEX
    Explanations

    button and buttons

    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
    adan
    -0.09
     Bir
    -0.08
    åĽŀ头
    -0.08
    çĥĽ
    -0.08
     Hawk
    -0.08
    èŃĺ
    -0.08
    èĩªçĦ¶èĢĮçĦ¶
    -0.08
    鸾
    -0.08
    rag
    -0.08
    é©¿ç«Ļ
    -0.08
    POSITIVE LOGITS
    æĮīéĴ®
    0.16
     button
    0.15
     buttons
    0.15
     кноп
    0.14
     btn
    0.13
    buttons
    0.13
    .button
    0.13
    button
    0.12
    /button
    0.11
     QPushButton
    0.11
    Activations Density 0.186%

    No Known Activations