© 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. 111617
    Prev
    Next
    INDEX
    Explanations

    without specific 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
    Negative Logits
     Mour
    -0.11
     Perc
    -0.10
    olon
    -0.10
     volunteering
    -0.10
     Sadd
    -0.10
    omore
    -0.10
    ogle
    -0.10
     Bolivia
    -0.10
     fil
    -0.10
     spont
    -0.10
    POSITIVE LOGITS
     exert
    0.13
     scarcely
    0.13
     hardly
    0.12
     barely
    0.12
     ever
    0.11
     recourse
    0.11
    udo
    0.10
     effort
    0.10
     actually
    0.10
     haven
    0.10
    Activations Density 0.077%

    No Known Activations