© 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. 52029
    Prev
    Next
    INDEX
    Explanations

    mouse click events

    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
    ç¬ijçĿĢ
    -0.09
    kw
    -0.09
    æĮĤçīĮ
    -0.09
    å¤ĩçĶ¨
    -0.09
    æĿ¥æī¾
    -0.09
    PLL
    -0.08
    opsis
    -0.08
    äºĮç»´çłģ
    -0.08
    Markdown
    -0.08
    NAL
    -0.08
    POSITIVE LOGITS
    é¼łæłĩ
    0.12
    -click
    0.10
     clicks
    0.10
    çĤ¹åĩ»
    0.10
     mouse
    0.10
    é¼ĵ
    0.10
    mouse
    0.10
    طا
    0.09
    (click
    0.09
    -events
    0.09
    Activations Density 0.187%

    No Known Activations