© 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. 47836
    Prev
    Next
    INDEX
    Explanations

    neonatal intensive care unit

    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
     slack
    -0.09
    rus
    -0.09
    åįķ身
    -0.09
    ç»Ī身
    -0.09
     пÑĢежде
    -0.09
    èİĺ
    -0.08
    plies
    -0.08
    åħļåijĺ
    -0.08
    欧
    -0.08
    åĢŁæѤ
    -0.08
    POSITIVE LOGITS
    æĸ°çĶŁåĦ¿
    0.11
     newborn
    0.11
    è¥ģ
    0.10
    åĩºçĶŁ
    0.10
    奶ç²ī
    0.10
    icus
    0.10
    ä¸İåıijå±ķ
    0.10
    .Param
    0.09
     neon
    0.09
    å¤Ń
    0.09
    Activations Density 0.305%

    No Known Activations