© 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. 112641
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     topo
    -0.09
     frantic
    -0.07
     crud
    -0.07
     reopening
    -0.07
    SEARCH
    -0.06
    udo
    -0.06
     Trilogy
    -0.06
     Rut
    -0.06
     bla
    -0.06
     Jer
    -0.06
    POSITIVE LOGITS
    itan
    0.13
     anymore
    0.13
     manifests
    0.12
     tard
    0.11
     Lyons
    0.11
     Andrews
    0.11
     manifest
    0.11
    482
    0.11
    obil
    0.11
     owing
    0.11
    Activations Density 0.000%

    No Known Activations