© 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. 17406
    Prev
    Next
    INDEX
    Explanations

    city/locality geographic location

    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
     frequ
    -0.11
     Frequ
    -0.10
     fore
    -0.10
     flav
    -0.10
     exotic
    -0.09
    ernet
    -0.09
     Active
    -0.09
     charg
    -0.09
    -map
    -0.09
     frequencies
    -0.09
    POSITIVE LOGITS
     anchors
    0.13
     spraw
    0.12
     mega
    0.12
     ag
    0.11
     largest
    0.11
     meg
    0.11
     sprawling
    0.10
     Largest
    0.10
     ance
    0.10
     enlarge
    0.10
    Activations Density 0.904%

    No Known Activations