© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16292
    Prev
    Next
    INDEX
    Explanations

    names like Jamie, Ethan, Marty

    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
     Susan
    -0.13
     Sue
    -0.12
     Carol
    -0.12
     Tina
    -0.12
     Barbara
    -0.12
     Sally
    -0.12
     Roger
    -0.12
     Linda
    -0.12
     Martha
    -0.11
     Chung
    -0.11
    POSITIVE LOGITS
     tattoos
    0.12
     tattoo
    0.11
     Cay
    0.11
    ryn
    0.11
     Calder
    0.10
     sui
    0.10
     hoodie
    0.10
     Eden
    0.10
     Reyes
    0.10
     Tristan
    0.10
    Activations Density 0.095%

    No Known Activations