© 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. 53430
    Prev
    Next
    INDEX
    Explanations

    medical advice due to

    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
    åIJ¬å¾Ĺ
    -0.10
    è¿Ļä¸ĢåĪ»
    -0.10
     hết
    -0.09
    ä»Ļ女
    -0.09
    ÙĪÙĬÙĦ
    -0.09
    å¹ķ
    -0.09
    çļĦéĢļçŁ¥
    -0.08
    æĥľ
    -0.08
    ë²
    -0.08
    æľªæĪIJå¹´
    -0.08
    POSITIVE LOGITS
    æĮª
    0.10
    罨
    0.08
    ä¸Ģ家
    0.08
    èķĥ
    0.08
    éĺŁä¼į
    0.08
    æ¹
    0.08
     Falls
    0.08
     Hoff
    0.07
    igo
    0.07
    åĮ¹
    0.07
    Activations Density 0.008%

    No Known Activations