© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40147
    Prev
    Next
    INDEX
    Explanations

    foreign influence and conflicts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    工夫
    -0.09
    åĬŁå¤«
    -0.09
    æ½ĩ
    -0.09
    èĢģ人家
    -0.09
    åĪĿäºĮ
    -0.08
    äºĮèĥİ
    -0.08
     tent
    -0.08
    -ish
    -0.08
    åij¼åĴĮ
    -0.08
    ä¸įéĶĻçļĦ
    -0.08
    POSITIVE LOGITS
    æŃª
    0.11
    è¨Ģè¡Į
    0.10
     Marr
    0.10
    çĭ¸
    0.10
    é¢łè¦Ĩ
    0.09
    çĤ®
    0.09
     меÑĢ
    0.09
    讹
    0.09
    çĭ¡
    0.09
    饱
    0.09
    Activations Density 0.081%

    No Known Activations