© 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. 113490
    Prev
    Next
    INDEX
    Explanations

    silver followed by light or spring

    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
     Welt
    -0.10
     McGr
    -0.09
    .jackson
    -0.09
    ysz
    -0.09
    cht
    -0.09
    sheet
    -0.09
    ible
    -0.09
    /null
    -0.09
    sect
    -0.08
    ëŀĺ
    -0.08
    POSITIVE LOGITS
     lining
    0.15
     Jub
    0.11
    stripe
    0.11
    stein
    0.11
    ado
    0.11
     gilt
    0.10
     plated
    0.10
    ware
    0.10
    heels
    0.10
    Stripe
    0.10
    Activations Density 0.030%

    No Known Activations