© 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. 32592
    Prev
    Next
    INDEX
    Explanations

    food items and meals

    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¿Ĺè¯Ŀ说
    -0.10
    æķĻä½ł
    -0.09
    Chef
    -0.09
    精油
    -0.09
    å°¼äºļ
    -0.09
    åݨæĪ¿
    -0.09
    ì§ģ
    -0.09
    çű
    -0.08
    unte
    -0.08
    åºŃéĻ¢
    -0.08
    POSITIVE LOGITS
    upa
    0.10
    ä¸Ģå°ı
    0.09
    åģı好
    0.09
     vict
    0.09
    structured
    0.09
    æīĢæıIJä¾Ľ
    0.09
    å°ijéĩı
    0.09
    å¾Īå°ı
    0.08
    nce
    0.08
    torrent
    0.08
    Activations Density 0.062%

    No Known Activations