© 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. 6566
    Prev
    Next
    INDEX
    Explanations

    wind and weather

    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
     snow
    -0.16
     skiing
    -0.14
     Snow
    -0.14
    snow
    -0.14
    Snow
    -0.14
     Rain
    -0.14
     rain
    -0.14
     surfing
    -0.13
     ski
    -0.13
     snowy
    -0.12
    POSITIVE LOGITS
     breeze
    0.17
     wind
    0.16
     clouds
    0.14
    wind
    0.13
     winds
    0.13
     sky
    0.12
     horizon
    0.12
     dew
    0.12
     surrounding
    0.11
     Wind
    0.11
    Activations Density 0.113%

    No Known Activations