© 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. 116214
    Prev
    Next
    INDEX
    Explanations

    illuminating or illumination

    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
    ulary
    -0.12
    alore
    -0.12
    alin
    -0.12
    edly
    -0.11
    lore
    -0.11
    entially
    -0.11
     embed
    -0.11
    irim
    -0.11
    Immutable
    -0.10
    edes
    -0.10
    POSITIVE LOGITS
     brightly
    0.14
    bright
    0.11
     pathway
    0.10
     pathways
    0.10
     bright
    0.09
     Targets
    0.09
     path
    0.09
     paths
    0.08
     targets
    0.08
     Lance
    0.08
    Activations Density 0.041%

    No Known Activations