© 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. 92291
    Prev
    Next
    INDEX
    Explanations

    following text strings

    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
     pomp
    -0.09
     omn
    -0.09
     entries
    -0.08
    emos
    -0.08
     unin
    -0.08
     affairs
    -0.08
    uned
    -0.08
     exhaustion
    -0.08
     withheld
    -0.08
     reve
    -0.08
    POSITIVE LOGITS
     intl
    0.11
     Gord
    0.10
     labs
    0.10
    uten
    0.10
     HOR
    0.10
     tort
    0.10
     intern
    0.10
     elder
    0.10
     Haus
    0.10
     elders
    0.10
    Activations Density 0.001%

    No Known Activations