© 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. 27882
    Prev
    Next
    INDEX
    Explanations

    urban locations

    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
     farms
    -0.10
     farming
    -0.10
     farm
    -0.10
    farm
    -0.09
     rural
    -0.09
     Finn
    -0.09
     farmhouse
    -0.08
    hor
    -0.08
     proprietary
    -0.08
    uted
    -0.08
    POSITIVE LOGITS
     Metropolitan
    0.14
     metropolitan
    0.13
    лиÑĨ
    0.12
     city
    0.12
     metro
    0.11
     neighborhoods
    0.11
    owntown
    0.11
     Downtown
    0.10
     suburb
    0.10
    city
    0.10
    Activations Density 0.027%

    No Known Activations