© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    reward or rewarded

    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
    å®°
    -0.24
    ULE
    -0.23
    ç©¿è¶Ĭ
    -0.23
    ä¿¡å¿ĥ
    -0.23
    è¯įæĿ¡
    -0.22
    rijk
    -0.22
    åĿļ飧
    -0.21
     Laugh
    -0.21
    Logged
    -0.21
    槽
    -0.21
    POSITIVE LOGITS
    çľ¼çľĭ
    0.28
    nite
    0.25
    ä¼ĺè´¨
    0.25
    å¥ĸåĬ±
    0.25
    ashi
    0.24
     rewarding
    0.24
     rewarded
    0.24
    æĥ©ç½ļ
    0.24
     reward
    0.23
    è¯Ħæ¯Ķ
    0.23
    Activations Density 0.064%

    No Known Activations