© 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. 31011
    Prev
    Next
    INDEX
    Explanations

    year month day time

    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
     nighttime
    -0.11
     daytime
    -0.11
    usi
    -0.10
     Prison
    -0.10
     Parade
    -0.10
     Dix
    -0.10
     midnight
    -0.10
     overnight
    -0.10
    ulls
    -0.10
     sometime
    -0.10
    POSITIVE LOGITS
     EDT
    0.12
     GMT
    0.12
     EST
    0.10
     UTC
    0.10
    aign
    0.10
     Greenwich
    0.09
     IST
    0.09
    agem
    0.09
     kern
    0.09
     NST
    0.09
    Activations Density 0.133%

    No Known Activations