© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3649
    Prev
    Next
    INDEX
    Explanations

    geological ages

    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
     nerv
    -0.11
    /team
    -0.11
     mirrors
    -0.11
    meno
    -0.10
     Mirror
    -0.10
     mirror
    -0.10
     Photon
    -0.10
    xico
    -0.10
    /Input
    -0.10
     withholding
    -0.10
    POSITIVE LOGITS
     fossils
    0.24
     geological
    0.24
     fossil
    0.24
     sediment
    0.20
     age
    0.20
     Geological
    0.18
     ge
    0.18
     ages
    0.17
     chron
    0.16
     epochs
    0.15
    Activations Density 0.472%

    No Known Activations