© 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. 29841
    Prev
    Next
    INDEX
    Explanations

    maintenance and care

    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
     recruiters
    -0.11
     innoc
    -0.11
     Firm
    -0.10
    å±Ģ
    -0.10
     entertain
    -0.10
     explos
    -0.10
     blunt
    -0.10
     Interr
    -0.10
     resisting
    -0.10
     uncomfort
    -0.10
    POSITIVE LOGITS
     maintenance
    0.50
     upkeep
    0.48
     care
    0.45
     Maintenance
    0.44
     caring
    0.43
     caret
    0.43
     cared
    0.39
    Maintenance
    0.38
    maintenance
    0.37
     Care
    0.37
    Activations Density 0.523%

    No Known Activations