© 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. 31973
    Prev
    Next
    INDEX
    Explanations

    total, totaled, totals, amounted, weighs

    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
    aji
    -0.12
     large
    -0.11
    iss
    -0.11
     sizable
    -0.10
     zero
    -0.10
     thousands
    -0.09
     longer
    -0.09
     dollars
    -0.09
    imir
    -0.09
     Eye
    -0.09
    POSITIVE LOGITS
     totaled
    0.18
     clocks
    0.17
     weighs
    0.17
     clock
    0.15
     Clock
    0.14
     amounted
    0.14
     totals
    0.13
     ranged
    0.13
     total
    0.13
    weigh
    0.13
    Activations Density 1.476%

    No Known Activations