© 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. 27731
    Prev
    Next
    INDEX
    Explanations

    married people or partners

    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
     Horror
    -0.09
     united
    -0.09
     Babies
    -0.09
    /MIT
    -0.09
     sadd
    -0.09
    pci
    -0.09
     Caller
    -0.09
     spec
    -0.09
    ìĺ
    -0.08
    eu
    -0.08
    POSITIVE LOGITS
    etto
    0.10
    ken
    0.10
    agna
    0.09
    untu
    0.09
    RD
    0.09
     Psy
    0.09
     Berk
    0.09
     residue
    0.09
    anka
    0.09
    bled
    0.09
    Activations Density 0.003%

    No Known Activations