© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113876
    Prev
    Next
    INDEX
    Explanations

    continents and 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
     worldwide
    -0.11
     globals
    -0.11
     Polar
    -0.10
     Globals
    -0.10
     globally
    -0.10
     global
    -0.10
     nationwide
    -0.10
    iets
    -0.09
     statewide
    -0.09
     Alpha
    -0.09
    POSITIVE LOGITS
     countries
    0.24
     Countries
    0.21
    Countries
    0.19
    countries
    0.17
     nations
    0.16
    -wide
    0.16
     region
    0.15
     languages
    0.14
    _countries
    0.14
     economies
    0.13
    Activations Density 0.584%

    No Known Activations