© 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. 113252
    Prev
    Next
    INDEX
    Explanations

    time references

    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
     regularly
    -0.13
     yearly
    -0.11
     monthly
    -0.11
     esl
    -0.10
     weekly
    -0.10
     Regular
    -0.10
     Fle
    -0.10
     recent
    -0.10
     periodically
    -0.10
     regular
    -0.10
    POSITIVE LOGITS
     Tonight
    0.12
     Tomorrow
    0.10
     tonight
    0.10
     deco
    0.10
     Saud
    0.09
    Tonight
    0.09
     itself
    0.09
    artz
    0.09
    usi
    0.09
     join
    0.09
    Activations Density 0.028%

    No Known Activations