© 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. 30009
    Prev
    Next
    INDEX
    Explanations

    wind activity and related phenomena

    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
     dripping
    -0.11
     hydrated
    -0.10
     amphib
    -0.10
     frog
    -0.10
     aquatic
    -0.10
     dri
    -0.09
     stain
    -0.09
     sme
    -0.09
    frog
    -0.09
     liquid
    -0.08
    POSITIVE LOGITS
     wind
    0.70
     winds
    0.63
     Wind
    0.59
    wind
    0.58
     windy
    0.56
    Wind
    0.55
     gust
    0.53
     Winds
    0.50
     storm
    0.47
    _wind
    0.47
    Activations Density 0.602%

    No Known Activations