© 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. 16060
    Prev
    Next
    INDEX
    Explanations

    elisabeth or spanish women

    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
    .nz
    -0.09
    hazi
    -0.09
    orget
    -0.09
    aciones
    -0.09
    hab
    -0.09
    Thin
    -0.09
    inox
    -0.09
     escalated
    -0.09
    ood
    -0.08
    opsis
    -0.08
    POSITIVE LOGITS
    boa
    0.14
    beth
    0.13
    bon
    0.12
    CDATA
    0.10
    ät
    0.10
    .newArrayList
    0.10
    abeth
    0.09
    plate
    0.09
     amb
    0.09
    iate
    0.09
    Activations Density 0.009%

    No Known Activations