© 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. 47913
    Prev
    Next
    INDEX
    Explanations

    Washington D.C. and other capitals

    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
    åĮħ袱
    -0.10
    åħ¨åİ¿
    -0.10
    lest
    -0.09
    Parm
    -0.09
     Parm
    -0.09
    笼
    -0.09
    æ¯ı次éĥ½
    -0.08
    å¥
    -0.08
    insky
    -0.08
    麸
    -0.08
    POSITIVE LOGITS
    é¦ĸéĥ½
    0.13
    京
    0.12
     Canberra
    0.12
    åĮĹ京
    0.11
    åĽ½ä¼ļ
    0.11
    æµ·æ·ĢåĮº
    0.11
    åľ¨äº¬
    0.11
    åįİçĽĽé¡¿
    0.11
     Washington
    0.10
     Islamabad
    0.10
    Activations Density 0.188%

    No Known Activations