© 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. 51698
    Prev
    Next
    INDEX
    Explanations

    million, amount, IDR, 100,000

    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
    è¿ijä¹İ
    -0.09
    çļĩ
    -0.09
     outnumber
    -0.09
    åģ¥
    -0.09
    ieee
    -0.09
    æĮ¨
    -0.08
     Huss
    -0.08
    íľ´
    -0.08
    ving
    -0.08
     Hak
    -0.08
    POSITIVE LOGITS
    è§Ħ模
    0.13
    è¦ı模
    0.12
    档次
    0.11
    ä¸Ģé¡¿
    0.10
    æłĩçļĦ
    0.10
    åĴĮ个人
    0.09
    åľ¨è·¯ä¸Ĭ
    0.09
    ç¡IJ
    0.09
    æĮīè§Ħå®ļ
    0.09
    çļĦèĥ½åĬĽ
    0.09
    Activations Density 0.056%

    No Known Activations