© 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. 46742
    Prev
    Next
    INDEX
    Explanations

    storm or weather events

    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
     sme
    -0.09
    &S
    -0.09
     distort
    -0.08
     oss
    -0.08
     staging
    -0.08
     scares
    -0.08
    MLS
    -0.08
    nek
    -0.08
    enario
    -0.08
    inel
    -0.08
    POSITIVE LOGITS
     storm
    0.17
    Storm
    0.16
     Storm
    0.16
     hurricanes
    0.15
     hurricane
    0.15
     hail
    0.14
     thunder
    0.14
     Hurricane
    0.14
     tornado
    0.14
     cycl
    0.14
    Activations Density 0.054%

    No Known Activations