© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8809
    Prev
    Next
    INDEX
    Explanations

    international, foreign, or abroad

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èµ·äºĨ
    -0.09
    åľ¨ç¾İåĽ½
    -0.09
    éĺ¿æĭī
    -0.09
     USA
    -0.08
    åIJ¸æ¯Ĵ
    -0.08
    ç¾İåĽ½
    -0.08
     Usa
    -0.08
    æīİ
    -0.08
     bitch
    -0.08
    USA
    -0.08
    POSITIVE LOGITS
    åħ¶ä»ĸåĽ½å®¶
    0.10
    çĪ±æĬ¤
    0.09
    çĶµä¿¡
    0.09
    æľįå½¹
    0.09
    å¯Ĵåģĩ
    0.09
    éĻįä»·
    0.09
    çļĩåŃIJ
    0.09
     PRI
    0.09
    æķħ宫
    0.09
    åĵį
    0.09
    Activations Density 0.150%

    No Known Activations