© 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. 89910
    Prev
    Next
    INDEX
    Explanations

    brand names like Be, Changan, DiGiCo, HyperX, Harman Kardon

    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
     Walt
    -0.11
    ucci
    -0.09
     abbreviated
    -0.09
    Warehouse
    -0.09
     petroleum
    -0.09
     Petroleum
    -0.09
    agua
    -0.09
     WWW
    -0.09
     punk
    -0.09
    azzi
    -0.09
    POSITIVE LOGITS
     device
    0.11
     devices
    0.11
     refl
    0.10
     Vander
    0.10
     digital
    0.10
     Kore
    0.10
    âĢ¦↵↵↵↵
    0.10
     Kund
    0.10
     webcam
    0.10
     sensor
    0.10
    Activations Density 0.024%

    No Known Activations