© 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. 7781
    Prev
    Next
    INDEX
    Explanations

    underwater scenes and marine life

    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
     wet
    -0.19
     pudd
    -0.17
     pool
    -0.17
     outdoors
    -0.16
     drying
    -0.16
     outdoor
    -0.16
     splash
    -0.16
     humid
    -0.16
     Wet
    -0.15
    splash
    -0.15
    POSITIVE LOGITS
     underwater
    0.27
     submarine
    0.22
     coral
    0.16
     seab
    0.15
     currents
    0.15
     depth
    0.15
     bottom
    0.15
     abyss
    0.15
     depths
    0.14
     reefs
    0.14
    Activations Density 1.037%

    No Known Activations