© 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. 48162
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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
    odie
    -0.11
     Highlander
    -0.09
     eta
    -0.09
     yourselves
    -0.09
    âĢij
    -0.09
     verd
    -0.09
     Surround
    -0.09
     seemingly
    -0.09
    رÙĪ
    -0.08
     rev
    -0.08
    POSITIVE LOGITS
     Bookmark
    0.14
     All
    0.12
     Enjoy
    0.12
     Hur
    0.12
     forget
    0.12
     We
    0.11
     hurry
    0.11
     Our
    0.11
     Go
    0.10
     Browse
    0.10
    Activations Density 0.044%

    No Known Activations