© 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. 8207
    Prev
    Next
    INDEX
    Explanations

    buying something

    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
     Glob
    -0.11
    endas
    -0.11
    /global
    -0.11
    uest
    -0.10
    orr
    -0.10
     bonding
    -0.10
     harb
    -0.10
     glob
    -0.10
     Aussie
    -0.10
     Clarkson
    -0.10
    POSITIVE LOGITS
    Dur
    0.08
     luckily
    0.08
    thew
    0.08
    akov
    0.08
    nah
    0.08
     Auswahl
    0.07
    await
    0.07
    riel
    0.07
     Maid
    0.07
     neighbour
    0.07
    Activations Density 0.001%

    No Known Activations