© 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. 47819
    Prev
    Next
    INDEX
    Explanations

    HTML doctype declarations

    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
    Disclaimer
    -0.17
     DISCLAIMER
    -0.13
     discharged
    -0.13
     discharge
    -0.13
     disclaimer
    -0.12
     Disclaimer
    -0.12
     disadvantaged
    -0.11
     disarm
    -0.11
     Disqus
    -0.11
     discretionary
    -0.11
    POSITIVE LOGITS
     notes
    0.13
     note
    0.12
     Notes
    0.12
    notes
    0.11
     NOTES
    0.10
    .chapter
    0.10
     recruiting
    0.10
    Notes
    0.10
     NOTE
    0.09
     cour
    0.09
    Activations Density 0.118%

    No Known Activations