© 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. 6650
    Prev
    Next
    INDEX
    Explanations

    countries or regions

    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
     barg
    -0.10
     omnip
    -0.09
     exerc
    -0.09
     persons
    -0.09
     Canadians
    -0.09
    porte
    -0.09
    bir
    -0.09
     wid
    -0.09
    assin
    -0.09
     Indianapolis
    -0.09
    POSITIVE LOGITS
     countries
    0.24
     Countries
    0.20
     regions
    0.20
    countries
    0.19
     where
    0.19
     jurisdictions
    0.18
     areas
    0.18
     cultures
    0.18
     nations
    0.17
     où
    0.16
    Activations Density 1.220%

    No Known Activations