© 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. 7971
    Prev
    Next
    INDEX
    Explanations

    patient experience, safety, and care

    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
    engl
    -0.09
    اء
    -0.09
    -0.09
    ../../../
    -0.09
    eday
    -0.08
    ç¨İè´¹
    -0.08
    å¹»æĥ³
    -0.08
    uster
    -0.08
    az
    -0.08
    rd
    -0.08
    POSITIVE LOGITS
    å°±åĮ»
    0.10
    arget
    0.10
    عÙĨÙĬ
    0.09
    [char
    0.09
    å®ĮäºĨ
    0.09
    orious
    0.09
    eenth
    0.09
    ience
    0.09
    ourney
    0.08
    ienza
    0.08
    Activations Density 0.038%

    No Known Activations