© 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. 3291
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and others

    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
    æıIJåĪ°
    -0.25
    quia
    -0.23
    æıIJ
    -0.22
     tant
    -0.22
    canonical
    -0.22
    æĬ¢åħĪ
    -0.22
    å¾Īé«ĺçļĦ
    -0.21
    scription
    -0.21
    å¯Ħ
    -0.21
    æĮĩ示
    -0.21
    POSITIVE LOGITS
     themselves
    0.82
     oneself
    0.81
    èĩªå·±çļĦ
    0.76
    èĩªå·±
    0.75
    èĩªèº«
    0.71
     yourself
    0.71
     herself
    0.70
     himself
    0.69
     itself
    0.68
     ÑģебÑı
    0.68
    Activations Density 0.128%

    No Known Activations