© 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. 15153
    Prev
    Next
    INDEX
    Explanations

    episode recap or preview

    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
     @{↵
    -0.09
    EEP
    -0.08
    âĢİ
    -0.08
     dramas
    -0.08
     seasons
    -0.08
     Categories
    -0.08
     tossing
    -0.08
     conflic
    -0.08
     Apps
    -0.08
     broadcasts
    -0.08
    POSITIVE LOGITS
     summary
    0.26
     Summary
    0.23
     recap
    0.20
     analysis
    0.20
     review
    0.19
     Analysis
    0.18
    Summary
    0.18
     Recap
    0.17
    Analysis
    0.17
    _summary
    0.17
    Activations Density 0.670%

    No Known Activations