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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56555
    Prev
    Next
    INDEX
    Explanations

    Sierra Leone

    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
    西èĹı
    -0.11
    åĨħèĴĻåı¤
    -0.11
    é«ĺåİŁ
    -0.10
    çıłæ±Ł
    -0.10
    æĬ¢
    -0.10
    举èİŀ
    -0.09
    åij¼åĴĮ浩çī¹
    -0.09
     Tibetan
    -0.09
    çĻ½äºij
    -0.09
    abad
    -0.09
    POSITIVE LOGITS
     Liberia
    0.10
    éĤ¦
    0.10
    éģĵè·¯
    0.09
    çľŁäºº
    0.09
    çļ®
    0.09
    ÙĪØ«
    0.09
    èµĦæºIJä¼ĺåĬ¿
    0.09
    ÙĬب
    0.09
    åįİçĽĽé¡¿
    0.08
     Baltimore
    0.08
    Activations Density 0.036%

    No Known Activations