© 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. 26461
    Prev
    Next
    INDEX
    Explanations

    Washington DC area publications

    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
     Ranch
    -0.13
     Yorkshire
    -0.13
     Bayern
    -0.12
    cond
    -0.11
     Akron
    -0.11
     Manitoba
    -0.10
     Auckland
    -0.10
     ranch
    -0.10
     Fiji
    -0.10
     statewide
    -0.10
    POSITIVE LOGITS
     Washington
    0.35
     DC
    0.31
     washington
    0.31
    Washington
    0.31
     Redskins
    0.29
     Georgetown
    0.28
     Bethesda
    0.27
     Maryland
    0.27
     Smithsonian
    0.24
     Arlington
    0.24
    Activations Density 1.018%

    No Known Activations