© 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. 113746
    Prev
    Next
    INDEX
    Explanations

    sequencing events

    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
    iah
    -0.13
    iev
    -0.11
    irse
    -0.11
    -org
    -0.10
    anske
    -0.10
    ér
    -0.10
    hud
    -0.10
    &apos
    -0.10
    aged
    -0.10
    hea
    -0.10
    POSITIVE LOGITS
     suddenly
    0.13
     once
    0.11
     abruptly
    0.11
     finally
    0.10
     gradually
    0.10
     when
    0.09
     then
    0.09
     after
    0.09
     proceeded
    0.09
     BAM
    0.08
    Activations Density 0.032%

    No Known Activations