© 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. 26680
    Prev
    Next
    INDEX
    Explanations

    rejuvenate, revitalize, energize

    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
     Mastery
    -0.10
    173
    -0.09
    lint
    -0.09
     mastery
    -0.09
    odore
    -0.09
     Kann
    -0.09
    oti
    -0.09
    .big
    -0.09
    Master
    -0.09
     Stable
    -0.09
    POSITIVE LOGITS
     rejuven
    0.22
     energ
    0.19
     Energ
    0.16
     recharge
    0.16
     vigor
    0.15
     replen
    0.15
     spiritually
    0.15
    /rest
    0.14
    -refresh
    0.14
     energies
    0.14
    Activations Density 0.023%

    No Known Activations