© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12551
    Prev
    Next
    INDEX
    Explanations

    Luxembourg and Belarus geopolitical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ç¬ķ
    -0.24
     skateboard
    -0.20
    å¿«æĬ¥
    -0.20
     Raleigh
    -0.19
    åİĨæĿ¥
    -0.19
    California
    -0.18
    æĿŃå·ŀ
    -0.18
    æĿŃå·ŀå¸Ĥ
    -0.18
    åŀ¢
    -0.18
    Mex
    -0.18
    POSITIVE LOGITS
     Luxembourg
    0.28
     Belarus
    0.24
     Belgian
    0.24
    ä¾Ĺ
    0.23
    éĥ§
    0.21
     Brussels
    0.20
    åįģåł°
    0.20
    ÑĤÑĮ
    0.19
    ish
    0.19
    çĽĤ
    0.19
    Activations Density 0.045%

    No Known Activations