© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57461
    Prev
    Next
    INDEX
    Explanations

    remembering gerunds

    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
    åģıåIJij
    -0.10
    ç»ıèIJ¥æ¨¡å¼ı
    -0.10
    æĸ°ä¸Ģè½®
    -0.09
    burger
    -0.09
    æĺ¾çĦ¶
    -0.09
    æ¯ķç«Ł
    -0.09
    åĤį
    -0.09
    à´´
    -0.09
    ritz
    -0.08
    å®ł
    -0.08
    POSITIVE LOGITS
    åĩłçĤ¹
    0.09
    ä¸įä¸ĭ
    0.09
    ngen
    0.09
    ys
    0.09
    ÑģÑĤа
    0.08
    为ä¼ģä¸ļ
    0.08
    ä¹Łæĺ¯å¦ĤæѤ
    0.08
    说æľį
    0.08
    Persistence
    0.08
    åĵ¥
    0.08
    Activations Density 0.034%

    No Known Activations