© 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. 5800
    Prev
    Next
    INDEX
    Explanations

    periods and punctuation

    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
     moreover
    -0.14
     furthermore
    -0.13
    Moreover
    -0.13
     Moreover
    -0.12
     anyway
    -0.11
     anyways
    -0.11
    And
    -0.11
    Furthermore
    -0.10
     THEN
    -0.10
     âĢº
    -0.10
    POSITIVE LOGITS
    ).↵↵
    0.11
     {}).
    0.10
     (↵↵
    0.10
    '.↵↵
    0.10
     blah
    0.10
    `.↵↵
    0.10
     Zub
    0.10
     --↵↵
    0.10
     /↵↵
    0.10
    ].↵↵
    0.10
    Activations Density 0.481%

    No Known Activations