© 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. 112931
    Prev
    Next
    INDEX
    Explanations

    preparing for 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
     accidental
    -0.11
     cheek
    -0.10
     forehead
    -0.10
     Bik
    -0.10
     Bold
    -0.09
     rebell
    -0.09
    abort
    -0.09
     Finder
    -0.09
     hugs
    -0.09
     ti
    -0.09
    POSITIVE LOGITS
     Tray
    0.11
     strapped
    0.11
     equip
    0.11
     cuc
    0.11
     preparations
    0.11
     wield
    0.10
     Preparation
    0.10
     preparation
    0.10
     prepare
    0.10
     prepared
    0.10
    Activations Density 0.029%

    No Known Activations