© 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. 50278
    Prev
    Next
    INDEX
    Explanations

    ocean, sea, beach, coast

    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
     underwater
    -0.19
     submerged
    -0.16
     aquatic
    -0.13
     swims
    -0.13
     Swim
    -0.12
     river
    -0.11
     swim
    -0.11
     Swimming
    -0.11
     snork
    -0.10
    river
    -0.10
    POSITIVE LOGITS
    front
    0.16
     views
    0.12
    -front
    0.12
    side
    0.12
    -view
    0.11
     Front
    0.11
     bree
    0.11
     view
    0.11
     smell
    0.11
     breeze
    0.11
    Activations Density 0.093%

    No Known Activations