© 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. 114051
    Prev
    Next
    INDEX
    Explanations

    ready for preparation

    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
     disemb
    -0.11
    ullo
    -0.11
     Cop
    -0.10
     spills
    -0.10
     spill
    -0.09
     Welcome
    -0.09
     Encounter
    -0.09
     pro
    -0.09
     Jays
    -0.09
     Stout
    -0.09
    POSITIVE LOGITS
     prepares
    0.26
     preparing
    0.26
     prepare
    0.26
     preparation
    0.25
     prepar
    0.24
     ready
    0.24
     preparations
    0.23
     Preparation
    0.22
     poised
    0.22
    Preparing
    0.20
    Activations Density 0.129%

    No Known Activations