© 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. 89152
    Prev
    Next
    INDEX
    Explanations

    wind and related concepts

    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
     nod
    -0.09
    andon
    -0.09
    nod
    -0.09
    compound
    -0.09
    esta
    -0.09
     Cosmos
    -0.09
     scram
    -0.09
    ileo
    -0.09
    /event
    -0.09
    PING
    -0.08
    POSITIVE LOGITS
    mill
    0.21
    screen
    0.16
     blowing
    0.16
     gust
    0.15
    sock
    0.14
    storms
    0.13
     turbines
    0.13
    SOR
    0.13
    igos
    0.13
    lass
    0.13
    Activations Density 0.038%

    No Known Activations