© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    insurance and insurers

    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
     prostitution
    -0.10
    airport
    -0.10
     flushed
    -0.10
     Democracy
    -0.10
     Kart
    -0.10
    olle
    -0.10
     Fist
    -0.10
     compost
    -0.10
     coh
    -0.10
     Bras
    -0.10
    POSITIVE LOGITS
     insurance
    0.59
     Insurance
    0.55
    Insurance
    0.54
    insurance
    0.51
     insurers
    0.48
     insured
    0.46
     insurer
    0.46
     insure
    0.40
     uninsured
    0.36
     premiums
    0.33
    Activations Density 0.750%

    No Known Activations