© 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. 25578
    Prev
    Next
    INDEX
    Explanations

    in advance

    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
     bedrooms
    -0.09
     Hold
    -0.09
     cuckold
    -0.09
    896
    -0.09
     World
    -0.09
     classrooms
    -0.08
     Chambers
    -0.08
     captivity
    -0.08
     fatt
    -0.08
     benefited
    -0.08
    POSITIVE LOGITS
     sick
    0.14
     reinforcements
    0.14
     fav
    0.12
    /request
    0.11
     favors
    0.10
     Sick
    0.10
     help
    0.10
     Graves
    0.10
     illness
    0.10
    credits
    0.10
    Activations Density 0.011%

    No Known Activations