© 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. 5508
    Prev
    Next
    INDEX
    Explanations

    shortly after

    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
    tz
    -0.11
     latter
    -0.10
    lod
    -0.10
    ç±
    -0.10
    slick
    -0.09
    burg
    -0.09
     zij
    -0.09
     deal
    -0.09
     later
    -0.09
    osity
    -0.09
    POSITIVE LOGITS
    uml
    0.11
    ytt
    0.09
    -ever
    0.09
    redd
    0.08
     Dew
    0.08
    ypes
    0.08
    mods
    0.08
    ivy
    0.08
     OCT
    0.08
    ue
    0.08
    Activations Density 0.003%

    No Known Activations