© 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. 7825
    Prev
    Next
    INDEX
    Explanations

    a sin

    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
    ä¸¥æł¼æī§è¡Į
    -0.10
    æĮ½
    -0.09
    çľ¼çľĭ
    -0.09
    Ùģرد
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
    ä¸¥æł¼æĮīçħ§
    -0.09
    æīij
    -0.08
    .nl
    -0.08
    attering
    -0.08
    IRC
    -0.08
    POSITIVE LOGITS
    åĥı
    0.10
     Dominion
    0.08
    TEGR
    0.08
    Cum
    0.08
     componentDidUpdate
    0.08
    åªļ
    0.08
    би
    0.08
    omit
    0.08
     reperc
    0.08
    åįı
    0.08
    Activations Density 0.106%

    No Known Activations