© 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. 3183
    Prev
    Next
    INDEX
    Explanations

    vertebral fractures or osteoporosis

    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
    æĢĢæĬ±
    -0.10
    ä¸Ģåī¯
    -0.10
    åºĸ
    -0.09
    è¿Ļ份
    -0.09
    allen
    -0.09
    ä¸ļä½Ļ
    -0.09
    æ°´éĿ¢
    -0.09
    涸
    -0.09
    å¾Ĺ天
    -0.09
    æ³»
    -0.09
    POSITIVE LOGITS
    olini
    0.10
    åĵģä½į
    0.09
    çĶ«
    0.08
    äºı
    0.08
    жÑĥ
    0.08
    æĦıæĦ¿
    0.08
    èģ·
    0.08
    æ¥ļ
    0.08
    .uc
    0.08
    éħį件
    0.08
    Activations Density 0.167%

    No Known Activations