© 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. 9504
    Prev
    Next
    INDEX
    Explanations

    pain and distress

    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
    èĶļ
    -0.09
    æ¿ij
    -0.09
    åIJ»
    -0.09
    太é«ĺ
    -0.09
    æ°ĹãģĮ
    -0.09
    åĩºå·®
    -0.08
    æ²ī积
    -0.08
    å¾Īæ¼Ĥ亮
    -0.08
    好人
    -0.08
    çĶľçĶľ
    -0.08
    POSITIVE LOGITS
     distress
    0.11
    çĥ¦æģ¼
    0.11
     sıkıntı
    0.09
    çĹĽèĭ¦
    0.09
    æĹłç©·
    0.09
    åĽ°æī°
    0.09
    巨大çļĦ
    0.09
    éĿŀåĩ¡
    0.09
    .uni
    0.09
    èĤīä½ĵ
    0.09
    Activations Density 0.047%

    No Known Activations