© 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. 6554
    Prev
    Next
    INDEX
    Explanations

    generate ssh key

    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
     Hunger
    -0.13
     hunger
    -0.12
     famine
    -0.10
     midnight
    -0.10
    umo
    -0.09
    -info
    -0.09
     refresh
    -0.09
     Synopsis
    -0.09
     cheats
    -0.09
    shortcut
    -0.09
    POSITIVE LOGITS
     supplies
    0.13
     Supplies
    0.12
     proc
    0.12
     fetched
    0.11
     fetch
    0.11
     sourcing
    0.11
     rum
    0.11
     kits
    0.11
     purchase
    0.11
     supplied
    0.11
    Activations Density 0.123%

    No Known Activations