© 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. 53343
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude

    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
    æ¯Ĵ
    -0.08
    å¼ķ
    -0.08
    鸢
    -0.08
    eken
    -0.08
    罪
    -0.08
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.08
    ewhat
    -0.07
    ought
    -0.07
    çĽ¸ä¼¼
    -0.07
    è¦ģæ¯Ķ
    -0.07
    POSITIVE LOGITS
    æĦŁæ¿Ģ
    0.20
    æĦŁè°¢
    0.17
    æĦŁè¬Ŀ
    0.15
    æĦŁåĬ¨
    0.14
     благодаÑĢ
    0.14
    谢谢
    0.12
     grateful
    0.12
    æĦŁæģ©
    0.12
    åıįè¿ĩæĿ¥
    0.12
     gratitude
    0.12
    Activations Density 0.045%

    No Known Activations