© 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. 89015
    Prev
    Next
    INDEX
    Explanations

    numbers; plural nouns

    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
     itself
    -0.09
     disposition
    -0.09
     lifestyle
    -0.08
    angu
    -0.08
     Prov
    -0.08
     Razor
    -0.08
    nid
    -0.08
     timid
    -0.08
    ery
    -0.08
     legislature
    -0.08
    POSITIVE LOGITS
     selves
    0.16
     respective
    0.16
     yourselves
    0.15
     respectively
    0.15
     histories
    0.13
    '
    0.12
    ’
    0.11
    elves
    0.11
    inar
    0.10
     reput
    0.10
    Activations Density 0.606%

    No Known Activations