© 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. 5197
    Prev
    Next
    INDEX
    Explanations

    years, dates, percentages

    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
     exc
    -0.09
     inert
    -0.08
     hone
    -0.08
     outs
    -0.08
     disturb
    -0.08
    annes
    -0.08
    NST
    -0.08
    kB
    -0.08
     suits
    -0.08
     suites
    -0.08
    POSITIVE LOGITS
    ëħ
    0.11
     roku
    0.10
    ppo
    0.10
     upcoming
    0.10
    å¹´
    0.10
     goat
    0.10
     Trends
    0.10
    currently
    0.10
     calendar
    0.10
     Strap
    0.10
    Activations Density 0.063%

    No Known Activations