© 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. 7667
    Prev
    Next
    INDEX
    Explanations

    meals and mealtimes

    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
    ä¼ij
    -0.11
    ç¥Ĺ
    -0.09
    CBS
    -0.09
    è·³
    -0.09
    磨
    -0.09
    æľīåĬ©
    -0.08
     Söz
    -0.08
    车åŃIJ
    -0.08
    åĬłå¿«åıijå±ķ
    -0.08
    績
    -0.08
    POSITIVE LOGITS
     meals
    0.15
    ä¸Ģé¡¿
    0.13
     meal
    0.13
    飨
    0.12
    é¥Ńèıľ
    0.11
    é¥Ń
    0.11
    饱
    0.11
     Meals
    0.11
    meal
    0.10
    é¡¿
    0.10
    Activations Density 0.073%

    No Known Activations