© 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. 51857
    Prev
    Next
    INDEX
    Explanations

    hospital discharge planning or length of stay

    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
    çıł
    -0.10
    导读
    -0.09
    æłī
    -0.09
    仪å¼ı
    -0.09
    åħ¼
    -0.09
    gaard
    -0.09
    berman
    -0.09
    ingredients
    -0.09
    Tiny
    -0.09
    æīĭåĬ¿
    -0.09
    POSITIVE LOGITS
    ä½ıéĻ¢
    0.12
    åħ¥
    0.11
     emergency
    0.11
    Stay
    0.09
    é©»
    0.09
    ä¸įä½ı
    0.09
    åĩºåħ¥
    0.09
     staying
    0.09
    è¾ĵ
    0.09
    çķĻ
    0.09
    Activations Density 0.225%

    No Known Activations