© 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. 23025
    Prev
    Next
    INDEX
    Explanations

    food preparation and scientific terms

    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
    çĽ¸å¹²
    -0.10
     nap
    -0.09
    å²Ĥ
    -0.09
    æĭĸ
    -0.09
    à¨Ĩ
    -0.09
    ä¸įæĢķ
    -0.09
    æīĺ
    -0.08
    èķĬ
    -0.08
    é¢ij
    -0.08
    ird
    -0.08
    POSITIVE LOGITS
    çĤĴ
    0.13
    éĶħ
    0.11
    éįĭ
    0.10
    çļĦçľ¼
    0.09
    第ä¸Ģä½į
    0.08
    çħĬ
    0.08
    ycl
    0.08
    å¥łå®ļ
    0.08
     Ernst
    0.08
    DataContext
    0.08
    Activations Density 0.180%

    No Known Activations