© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    San Francisco and California 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
    Negative Logits
     Arkansas
    -0.14
     Florida
    -0.14
     Bangkok
    -0.13
     Tulsa
    -0.13
     florida
    -0.13
     Memphis
    -0.12
     Disney
    -0.12
     desert
    -0.12
     Cherokee
    -0.12
     Oklahoma
    -0.12
    POSITIVE LOGITS
     SF
    0.26
     Oakland
    0.26
     Berkeley
    0.24
     Stanford
    0.22
     Yosemite
    0.22
     Marin
    0.22
     San
    0.21
    SF
    0.21
     Monterey
    0.21
     sf
    0.20
    Activations Density 1.726%

    No Known Activations