© 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. 26789
    Prev
    Next
    INDEX
    Explanations

    Lebanese author

    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
    ertz
    -0.08
    .Bottom
    -0.08
    BTN
    -0.08
    ↵↵↵↵
    -0.07
    conte
    -0.07
    udi
    -0.07
    705
    -0.06
    hta
    -0.06
    aeda
    -0.06
    ).↵↵↵
    -0.06
    POSITIVE LOGITS
     âĢ
    0.11
    amma
    0.10
     snug
    0.09
     Hayden
    0.09
     recip
    0.09
     âĢŀ
    0.09
    hic
    0.09
    /Form
    0.09
     biz
    0.09
     unfortunate
    0.08
    Activations Density 0.006%

    No Known Activations