© 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. 115061
    Prev
    Next
    INDEX
    Explanations

    application characteristics

    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
    lah
    -0.10
     Dol
    -0.09
     Simon
    -0.09
    Uvs
    -0.09
    Ë
    -0.09
    purple
    -0.08
    ideos
    -0.08
     lax
    -0.08
     Atmos
    -0.08
     purple
    -0.08
    POSITIVE LOGITS
     wearer
    0.10
     Tong
    0.10
    ROI
    0.10
     brows
    0.09
     Dalton
    0.09
     infra
    0.09
     carriers
    0.09
     carrier
    0.09
     Hawks
    0.09
     licked
    0.09
    Activations Density 0.072%

    No Known Activations