© 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. 8049
    Prev
    Next
    INDEX
    Explanations

    calculate arithmetic calculations

    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
    ...(
    -0.10
    esson
    -0.10
     organised
    -0.10
    owntown
    -0.09
    verts
    -0.09
    _connect
    -0.09
     Âł Âł Âł Âł
    -0.09
    >Your
    -0.09
     MacDonald
    -0.09
    _"
    -0.09
    POSITIVE LOGITS
     worth
    0.10
     Worth
    0.10
     guarante
    0.09
     Este
    0.09
    asel
    0.08
     gossip
    0.08
    worth
    0.08
     Widow
    0.08
     ripe
    0.08
    [url
    0.08
    Activations Density 0.183%

    No Known Activations