© 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. 113095
    Prev
    Next
    INDEX
    Explanations

    sky - NET, -high, way, line, Harbor, Sports

    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
     wik
    -0.10
    mate
    -0.10
    enia
    -0.10
    mk
    -0.09
    site
    -0.09
    igg
    -0.09
    iston
    -0.09
     unde
    -0.09
     mang
    -0.09
     sketches
    -0.09
    POSITIVE LOGITS
    ward
    0.15
    -reaching
    0.12
    rocket
    0.11
    rim
    0.11
    fall
    0.11
    -blue
    0.11
    walker
    0.11
     above
    0.11
    hooks
    0.11
    wards
    0.10
    Activations Density 0.042%

    No Known Activations