© 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. 5221
    Prev
    Next
    INDEX
    Explanations

    after the war and reconstruction

    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
     Crisis
    -0.13
     pan
    -0.11
    ASF
    -0.11
     escalation
    -0.11
    Workflow
    -0.11
     Coronavirus
    -0.11
     PAN
    -0.10
     outbreak
    -0.10
    qli
    -0.10
     crisis
    -0.10
    POSITIVE LOGITS
     post
    0.28
     rebuilding
    0.24
     reconstruction
    0.23
     rebuild
    0.22
     Reconstruction
    0.22
     Post
    0.21
     rebuilt
    0.19
    post
    0.18
    Post
    0.18
     reconstructed
    0.17
    Activations Density 0.697%

    No Known Activations