© 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. 115891
    Prev
    Next
    INDEX
    Explanations

    urban/rural areas

    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
     Portuguese
    -0.09
     receptive
    -0.09
    lod
    -0.09
     Rooney
    -0.09
     Noon
    -0.09
    olor
    -0.09
     reopen
    -0.09
     coinc
    -0.09
     conc
    -0.09
     Transparent
    -0.08
    POSITIVE LOGITS
     urban
    0.43
    urban
    0.38
     rural
    0.38
     Urban
    0.37
    Urban
    0.33
     Rural
    0.32
     suburban
    0.30
     countryside
    0.29
     urb
    0.28
     city
    0.26
    Activations Density 0.250%

    No Known Activations