© 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. 30179
    Prev
    Next
    INDEX
    Explanations

    columbus, columbia, columbian

    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
     downstairs
    -0.09
     surplus
    -0.09
     Bast
    -0.09
    ube
    -0.09
    erm
    -0.09
     bil
    -0.09
     fond
    -0.09
    y
    -0.09
    yo
    -0.08
    onomic
    -0.08
    POSITIVE LOGITS
     colum
    0.16
     Columbus
    0.15
     Colum
    0.14
    bian
    0.14
    bus
    0.13
    andel
    0.13
     arous
    0.11
    bic
    0.11
    bine
    0.10
    ibia
    0.10
    Activations Density 0.026%

    No Known Activations