© 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. 112815
    Prev
    Next
    INDEX
    Explanations

    "this" followed by news or events

    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
    stad
    -0.12
     principle
    -0.11
    itational
    -0.11
     Fleming
    -0.10
    oba
    -0.10
     <",
    -0.10
     impover
    -0.10
    ingles
    -0.10
     Klo
    -0.10
    itu
    -0.10
    POSITIVE LOGITS
     unexpected
    0.13
     setback
    0.10
     revelation
    0.10
     development
    0.10
     setbacks
    0.09
     remark
    0.09
     new
    0.09
     intrusion
    0.09
     news
    0.09
     Development
    0.09
    Activations Density 0.015%

    No Known Activations