© 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. 7821
    Prev
    Next
    INDEX
    Explanations

    file, tract, system, input, website

    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
     thanks
    -0.15
     courtesy
    -0.14
     due
    -0.11
    inking
    -0.11
    thanks
    -0.11
     Howell
    -0.10
    due
    -0.10
    handled
    -0.10
     owing
    -0.09
     mish
    -0.09
    POSITIVE LOGITS
     efficiently
    0.13
    ngo
    0.12
     indirectly
    0.11
     quickly
    0.11
     effectively
    0.10
     safely
    0.10
     accurately
    0.10
     securely
    0.10
     easily
    0.09
     quicker
    0.09
    Activations Density 1.078%

    No Known Activations