© 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. 29052
    Prev
    Next
    INDEX
    Explanations

    restore, restoration, or restorative action

    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
    nable
    -0.11
     Libre
    -0.10
     goodbye
    -0.10
    uous
    -0.10
    sta
    -0.10
    Selectors
    -0.10
     stron
    -0.10
     Zukunft
    -0.10
    elen
    -0.09
    sand
    -0.09
    POSITIVE LOGITS
     balance
    0.14
     faith
    0.13
     confidence
    0.12
     harmony
    0.11
    InstanceState
    0.11
     Sanity
    0.11
     sanity
    0.11
     balances
    0.10
     Balance
    0.10
     peace
    0.10
    Activations Density 0.045%

    No Known Activations