© 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. 5122
    Prev
    Next
    INDEX
    Explanations

    ancestry research family history

    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
     Humb
    -0.10
     observation
    -0.10
     robber
    -0.10
     observer
    -0.10
     Sanct
    -0.10
     mime
    -0.10
    MessageType
    -0.10
     observers
    -0.10
     arrest
    -0.10
    Observer
    -0.10
    POSITIVE LOGITS
     ancestry
    0.45
     ancestral
    0.37
     ancestor
    0.36
     ancestors
    0.36
     lineage
    0.34
     descendants
    0.32
     ancest
    0.31
     heritage
    0.31
     gene
    0.30
     descendant
    0.30
    Activations Density 0.947%

    No Known Activations