© 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. 7931
    Prev
    Next
    INDEX
    Explanations

    hats and sunglasses

    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
    rug
    -0.11
     fortified
    -0.10
     dma
    -0.10
     Christmas
    -0.10
    adem
    -0.10
    [from
    -0.10
     woven
    -0.10
     Orn
    -0.09
    اد
    -0.09
    aad
    -0.09
    POSITIVE LOGITS
     Manual
    0.11
     wrongly
    0.10
     mistakenly
    0.10
    vk
    0.10
    Manual
    0.10
     manual
    0.10
     trendy
    0.10
     incorrectly
    0.09
     mode
    0.09
    Mode
    0.09
    Activations Density 0.027%

    No Known Activations