© 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. 18443
    Prev
    Next
    INDEX
    Explanations

    childhood to adulthood

    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
     originally
    -0.10
     originals
    -0.09
    owe
    -0.09
     Ancient
    -0.09
    ago
    -0.09
     Originally
    -0.08
     ancient
    -0.08
     beforehand
    -0.08
     ej
    -0.08
     Anc
    -0.08
    POSITIVE LOGITS
     adult
    0.36
     adulthood
    0.34
     Adult
    0.29
     adults
    0.28
     later
    0.27
    adult
    0.27
    Adult
    0.27
     Adults
    0.24
     grown
    0.23
     adolescence
    0.23
    Activations Density 0.281%

    No Known Activations