© 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. 7692
    Prev
    Next
    INDEX
    Explanations

    food supply, security, protection, goods, crops

    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
    æ´¾åĩº
    -0.09
    æĺı
    -0.09
    UNC
    -0.09
     мил
    -0.09
    æĹłåı¯
    -0.08
    寿
    -0.08
    unga
    -0.08
    iba
    -0.08
    è°Ł
    -0.08
    éŨçªĹ
    -0.08
    POSITIVE LOGITS
    çĶŁäº§åĴĮ
    0.10
    çļĦå®īåħ¨
    0.09
    ä¾Ľç»Ļ
    0.09
    æĹ©çĤ¹
    0.09
    åıĺ
    0.09
    opal
    0.08
     Morm
    0.08
    è¿ľ
    0.08
    -security
    0.08
    ä¾ĽåºĶ
    0.08
    Activations Density 0.035%

    No Known Activations