© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30456
    Prev
    Next
    INDEX
    Explanations

    with subsequent word

    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
     Fritz
    -0.09
    ritz
    -0.08
    dff
    -0.08
     dom
    -0.08
     heading
    -0.07
     Wolfgang
    -0.07
     Blanc
    -0.07
    /mobile
    -0.07
    ippy
    -0.07
     detriment
    -0.07
    POSITIVE LOGITS
     highways
    0.13
     suburbs
    0.11
     college
    0.11
     unemployment
    0.10
    /Page
    0.10
     GDP
    0.10
     Highway
    0.10
     economy
    0.10
    ihan
    0.09
     normal
    0.09
    Activations Density 2.573%

    No Known Activations