© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116562
    Prev
    Next
    INDEX
    Explanations

    Romanian language and geography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     Jes
    -0.11
     àª
    -0.10
    àª
    -0.10
     mess
    -0.10
     MarÃŃa
    -0.10
    644
    -0.10
     alph
    -0.09
     preca
    -0.09
     Olive
    -0.09
     divid
    -0.09
    POSITIVE LOGITS
     Romanian
    0.30
     Romania
    0.27
    Äĥ
    0.23
    ÈĽ
    0.21
    ÈĻ
    0.19
     pentru
    0.18
     în
    0.18
     cÄĥ
    0.18
    È
    0.17
     ÈĻi
    0.17
    Activations Density 0.235%

    No Known Activations