© 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. 112346
    Prev
    Next
    INDEX
    Explanations

    water-related words

    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
     extras
    -0.09
     Fut
    -0.09
     Mes
    -0.08
    Fabric
    -0.08
     Armour
    -0.08
     datastore
    -0.08
     Jung
    -0.08
    enberg
    -0.08
    arella
    -0.08
     Extras
    -0.08
    POSITIVE LOGITS
     baptism
    0.15
    logged
    0.13
     bapt
    0.13
    melon
    0.12
     scarcity
    0.12
     hydration
    0.12
     boiling
    0.12
    loo
    0.11
     hydr
    0.11
     splash
    0.11
    Activations Density 0.196%

    No Known Activations