© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33985
    Prev
    Next
    INDEX
    Explanations

    locations of facilities and states

    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
    Negative Logits
     subway
    -0.16
     street
    -0.15
     Street
    -0.14
     Urban
    -0.13
     metro
    -0.13
     Metro
    -0.12
     urban
    -0.12
     STREET
    -0.12
    Street
    -0.12
     homeless
    -0.11
    POSITIVE LOGITS
     ranch
    0.22
     Ranch
    0.18
     broth
    0.17
     rooms
    0.17
     Nevada
    0.15
     cott
    0.14
     bunk
    0.14
     bordel
    0.14
     bord
    0.13
    Rooms
    0.13
    Activations Density 0.038%

    No Known Activations