© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1246
    Prev
    Next
    INDEX
    Explanations

    Poland or Polish places and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     Nevada
    -0.32
    æĿŃ
    -0.31
    æ¼ĵ
    -0.30
     Tahoe
    -0.29
     Californ
    -0.29
    æĿŃå·ŀå¸Ĥ
    -0.29
    åĬłå·ŀ
    -0.29
    California
    -0.29
    婺
    -0.29
     UCLA
    -0.28
    POSITIVE LOGITS
     Polish
    0.59
    æ³¢åħ°
    0.57
     Warsaw
    0.52
     Poland
    0.49
     Pols
    0.42
     Belarus
    0.40
     Slovak
    0.40
    æ¾½
    0.39
     GdaÅĦsk
    0.37
    ÅĤ
    0.36
    Activations Density 0.343%

    No Known Activations