© 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. 7977
    Prev
    Next
    INDEX
    Explanations

    endocrine cells

    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
    被åĬ¨
    -0.10
    iren
    -0.10
    à´´
    -0.10
    æĺ¾
    -0.09
    黾
    -0.09
    arians
    -0.09
    оÑĩной
    -0.08
     Bair
    -0.08
    æĹ·
    -0.08
    æīĺ
    -0.08
    POSITIVE LOGITS
    æ±ŁåĮĹ
    0.09
     demographics
    0.08
     segment
    0.08
    èĻļ
    0.08
    çĴĭ
    0.08
    IMP
    0.08
    ifs
    0.08
    宵
    0.08
     demographic
    0.08
    çľ¼ä¸Ń
    0.08
    Activations Density 0.324%

    No Known Activations