© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3144
    Prev
    Next
    INDEX
    Explanations

    verbs of speaking and saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    èĩĤ
    -0.26
     Aust
    -0.24
    çľ¼çķĮ
    -0.23
    æľºåħ³
    -0.23
    æķĿ
    -0.23
    åĩ¸
    -0.23
    æł·çļĦ
    -0.22
    褶
    -0.22
     Daniels
    -0.22
    åħ¨éĿ¢
    -0.21
    POSITIVE LOGITS
    äºĨä¸Ģåı¥
    0.33
    ä¸Ģåı¥
    0.30
     audible
    0.29
    åĩłåı¥
    0.28
     heard
    0.28
     words
    0.28
     louder
    0.27
    äºĨä¸Ģ声
    0.26
    è¿Ļåı¥è¯Ŀ
    0.26
     softly
    0.26
    Activations Density 0.021%

    No Known Activations