© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16287
    Prev
    Next
    INDEX
    Explanations

    firefighter and rescue

    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
     ark
    -0.11
    Blo
    -0.10
     cond
    -0.10
    stalk
    -0.10
     rico
    -0.10
     Rao
    -0.10
     cruc
    -0.10
     Blo
    -0.10
     Boutique
    -0.10
     Stones
    -0.09
    POSITIVE LOGITS
     firefighter
    0.43
     firefighters
    0.43
     firefight
    0.40
     Fire
    0.29
     fire
    0.29
     extingu
    0.27
     rescue
    0.26
    Fire
    0.25
     Rescue
    0.23
     resc
    0.22
    Activations Density 0.350%

    No Known Activations