© 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. 3343
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs before pronouns

    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
     ÐIJлекÑģан
    -0.27
     ÐŁÐ¾Ñĩем
    -0.22
     ÐĶмиÑĤÑĢ
    -0.22
     occurrence
    -0.22
    aepernick
    -0.22
    åı¯æĥ³èĢĮçŁ¥
    -0.21
     improper
    -0.21
    ìłľ
    -0.21
    åı¯èĥ½å¯¼èĩ´
    -0.21
     consequence
    -0.21
    POSITIVE LOGITS
    ä»ĸ们
    0.46
    å®ĥ
    0.45
     you
    0.45
    ä»ĸåľ¨
    0.44
    ä»ĸ
    0.44
     they
    0.41
    她
    0.40
    ä»ĸä»¬åľ¨
    0.38
    ä»ĸåıĪ
    0.38
    å®ĥ们
    0.36
    Activations Density 0.420%

    No Known Activations