© 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. 6890
    Prev
    Next
    INDEX
    Explanations

    seattle washington

    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
     Newfoundland
    -0.11
     Monterey
    -0.11
     Californ
    -0.11
     provincial
    -0.11
     Rupert
    -0.11
     UCS
    -0.10
     Alberta
    -0.10
     province
    -0.09
     Provincial
    -0.09
     Canadians
    -0.09
    POSITIVE LOGITS
     Seattle
    0.24
    Seattle
    0.21
     Seahawks
    0.20
     Microsoft
    0.15
     Tacoma
    0.15
     Pu
    0.15
     Washington
    0.14
    Microsoft
    0.13
     Yak
    0.13
     UW
    0.13
    Activations Density 0.230%

    No Known Activations