© 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. 5587
    Prev
    Next
    INDEX
    Explanations

    date context

    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
     dates
    -0.17
    dates
    -0.14
     date
    -0.13
    _dates
    -0.12
    date
    -0.12
     Dates
    -0.12
    dating
    -0.12
     dating
    -0.11
    Dates
    -0.11
     dated
    -0.11
    POSITIVE LOGITS
    iname
    0.10
    stamp
    0.10
    /time
    0.10
    ape
    0.10
     Mond
    0.10
     arriving
    0.09
    UTC
    0.09
    esi
    0.09
     gam
    0.09
    isas
    0.09
    Activations Density 0.047%

    No Known Activations