© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111658
    Prev
    Next
    INDEX
    Explanations

    life spent or devoted

    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
     permanently
    -0.12
     momentarily
    -0.11
     temporarily
    -0.10
     permanent
    -0.10
    bnb
    -0.09
     globally
    -0.09
     Tout
    -0.09
     Bren
    -0.09
    GS
    -0.09
     daily
    -0.09
    POSITIVE LOGITS
     ago
    0.14
     Ago
    0.14
     spent
    0.13
    -long
    0.12
    ago
    0.12
     devoted
    0.10
    -old
    0.10
    hart
    0.10
    oria
    0.10
     dedication
    0.10
    Activations Density 0.057%

    No Known Activations