© 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. 5486
    Prev
    Next
    INDEX
    Explanations

    Voyager, Janeway, Borg, Torres, Kathryn

    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
     Illinois
    -0.11
     PSA
    -0.10
     Orn
    -0.10
     Oracle
    -0.10
     cherry
    -0.10
     CPS
    -0.09
     cerc
    -0.09
     Facebook
    -0.09
     Slack
    -0.09
     Ike
    -0.09
    POSITIVE LOGITS
     Voyager
    0.23
     Borg
    0.15
     Torres
    0.14
     Kes
    0.13
     assim
    0.12
     Kathryn
    0.12
    .numpy
    0.11
     Marcel
    0.11
     Voy
    0.11
    voy
    0.11
    Activations Density 0.226%

    No Known Activations