© 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. 112954
    Prev
    Next
    INDEX
    Explanations

    numbers followed by 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
    finally
    -0.13
     Conclusion
    -0.11
    Finally
    -0.11
    Conclusion
    -0.11
     finally
    -0.11
     Finally
    -0.11
    Lastly
    -0.10
     Uncategorized
    -0.10
    721
    -0.10
    erna
    -0.10
    POSITIVE LOGITS
     Dit
    0.12
     Speaking
    0.10
     similarly
    0.09
     closely
    0.09
     likewise
    0.09
    halt
    0.09
    oire
    0.09
     instit
    0.09
    irut
    0.09
     off
    0.09
    Activations Density 0.356%

    No Known Activations