© 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. 51838
    Prev
    Next
    INDEX
    Explanations

    research and development

    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
    奴
    -0.09
    嵯
    -0.09
    esses
    -0.09
    妾
    -0.09
    /environment
    -0.09
    å¥ı
    -0.09
    ittings
    -0.09
    dex
    -0.08
    åħ¨å¥Ĺ
    -0.08
    åĢij
    -0.08
    POSITIVE LOGITS
    uce
    0.11
    æĢ¯
    0.09
    tips
    0.08
    bye
    0.08
    æĽĻ
    0.08
    ward
    0.08
    åľ¨æ¸¸æĪıä¸Ń
    0.08
    .inst
    0.08
    fer
    0.08
    iad
    0.08
    Activations Density 0.013%

    No Known Activations