© 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. 117416
    Prev
    Next
    INDEX
    Explanations

    word endings: -fed, -ained, -binding, -ried

    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
     Desert
    -0.09
     Formula
    -0.09
     Dod
    -0.09
     dod
    -0.08
     Merr
    -0.08
     lest
    -0.08
    mere
    -0.08
     Interracial
    -0.07
     Baron
    -0.07
     peripheral
    -0.07
    POSITIVE LOGITS
     fertile
    0.12
    SSID
    0.12
    pane
    0.12
    /cop
    0.11
    eft
    0.11
    lei
    0.10
    =end
    0.10
    assi
    0.10
     exacerb
    0.10
    tras
    0.10
    Activations Density 0.001%

    No Known Activations