© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51397
    Prev
    Next
    INDEX
    Explanations

    bone fractures and healing

    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
    æĺŃ
    -0.10
    æľ¬ç½ijç«Ļ
    -0.09
    ÑģÑģ
    -0.09
    æĬ¥èĢĥ
    -0.09
    涪
    -0.09
    è¯ĺ
    -0.09
    automation
    -0.08
     Scri
    -0.08
     dise
    -0.08
    ä¿ĥ
    -0.08
    POSITIVE LOGITS
    骨æĬĺ
    0.14
    骨
    0.11
     bone
    0.11
    æĺ¯æľĢ
    0.10
    骨头
    0.10
    ç¢İ
    0.09
    骨骼
    0.09
    ç²īç¢İ
    0.09
     bones
    0.09
    çł´ç¢İ
    0.08
    Activations Density 0.117%

    No Known Activations