© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3578
    Prev
    Next
    INDEX
    Explanations

    Netherlands and Dutch locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zich
    -0.10
     toch
    -0.10
     bö
    -0.09
     bild
    -0.09
     komen
    -0.09
     echt
    -0.09
    GU
    -0.08
     fick
    -0.08
    beit
    -0.08
     Edmund
    -0.08
    POSITIVE LOGITS
    .nl
    0.21
     Dutch
    0.21
     van
    0.19
     Amsterdam
    0.19
     Netherlands
    0.17
     Rotterdam
    0.16
     Holland
    0.15
     Van
    0.15
     Een
    0.15
     dikke
    0.15
    Activations Density 0.728%

    No Known Activations