© 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. 61807
    Prev
    Next
    INDEX
    Explanations

    Dutch and Netherlands locations

    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
    ç¦Ģ
    -0.09
    æ¡¢
    -0.09
    çī¹æľĹ
    -0.09
    PCM
    -0.09
    scape
    -0.09
    çħ§äº®
    -0.09
    éĨį
    -0.09
    åķľ
    -0.09
    ä¾Ĺ
    -0.09
    å¿»
    -0.09
    POSITIVE LOGITS
    èį·åħ°
    0.24
     Dutch
    0.21
    .nl
    0.18
     van
    0.17
     Amsterdam
    0.17
     Netherlands
    0.16
     Rotterdam
    0.13
     amsterdam
    0.13
     Nederland
    0.13
     Holland
    0.12
    Activations Density 0.355%

    No Known Activations