© 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. 3269
    Prev
    Next
    INDEX
    Explanations

    money, revenue, cost, price

    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
    çıŃéķ¿
    -0.26
     governor
    -0.26
    åĦ¿ç§ij
    -0.26
    åľ¨å½ĵåľ°
    -0.25
    rtle
    -0.24
    å¾Īæ¼Ĥ亮
    -0.24
     Safety
    -0.24
    .ast
    -0.24
    åı¸ä»¤
    -0.24
    è¯¥æł¡
    -0.23
    POSITIVE LOGITS
    æĢ»éĩı
    0.39
     monet
    0.36
    ä»ĺè´¹
    0.35
    æ¶Īè´¹èĢħ
    0.33
    åķĨä¸ļ模å¼ı
    0.33
     revenue
    0.33
    è¶ĬæĿ¥è¶Ĭå°ij
    0.32
    éĶĢéĩı
    0.32
    åĩºçīĪ
    0.32
    å»īä»·
    0.31
    Activations Density 0.035%

    No Known Activations