© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35606
    Prev
    Next
    INDEX
    Explanations

    Dutch places and Netherlands

    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
    称
    -0.10
    è·Łè¿Ľ
    -0.10
    è±¢
    -0.09
    éĻķ
    -0.09
    绥
    -0.08
    éĴ¦
    -0.08
    èħ®
    -0.08
    潸
    -0.08
    å³Ń
    -0.08
    寨
    -0.08
    POSITIVE LOGITS
    èį·åħ°
    0.23
     Dutch
    0.20
     Netherlands
    0.18
    .nl
    0.16
     Nederland
    0.16
    èį·
    0.16
     Holland
    0.15
     Amsterdam
    0.14
     Rotterdam
    0.14
     van
    0.13
    Activations Density 0.196%

    No Known Activations