© 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. 30039
    Prev
    Next
    INDEX
    Explanations

    cities

    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
     Libyan
    -0.16
     Moroccan
    -0.15
     Thai
    -0.14
     Welsh
    -0.14
     Icelandic
    -0.14
     Hawaiian
    -0.14
    Thai
    -0.13
     Danish
    -0.13
     Hungarian
    -0.13
     Malaysian
    -0.13
    POSITIVE LOGITS
     Europe
    0.20
     cities
    0.20
     London
    0.19
     Rome
    0.18
     Italy
    0.18
     town
    0.18
     Mexico
    0.18
     Germany
    0.17
     England
    0.17
     Antarctica
    0.17
    Activations Density 1.733%

    No Known Activations