© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
    æıIJä¾ĽæĽ´å¤ļ
    -0.26
    æĽ´å¼º
    -0.25
     further
    -0.24
     eventual
    -0.24
    ä»ħä¾ĽåıĤèĢĥ
    -0.24
    endif
    -0.24
    udios
    -0.23
     future
    -0.23
    谢谢
    -0.23
     misc
    -0.23
    POSITIVE LOGITS
    åħĪæĺ¯
    0.34
    èµ·åĪĿ
    0.34
    æľ¬æĿ¥
    0.30
    ä¹ĭåĪĿ
    0.29
    åİŁæľ¬
    0.28
    ä¸Ģå¼Ģå§ĭ
    0.27
    说æĺ¯
    0.26
    æľĢåĪĿ
    0.26
    ä¹ĭæīĢ以
    0.26
    ä½Ĩåį´
    0.26
    Activations Density 0.252%

    No Known Activations