© 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. 113054
    Prev
    Next
    INDEX
    Explanations

    employment intermediary

    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
     Imm
    -0.11
    priority
    -0.10
    ddb
    -0.10
     volunteering
    -0.10
     unab
    -0.10
    ADING
    -0.10
     voluntarily
    -0.10
     priority
    -0.10
    iken
    -0.10
     Exhaust
    -0.10
    POSITIVE LOGITS
     intermediary
    0.51
     intermedi
    0.51
     intermediate
    0.38
     indirect
    0.32
     mediation
    0.29
     intervening
    0.28
     middle
    0.27
    Intermediate
    0.27
     mediator
    0.27
     Intermediate
    0.26
    Activations Density 1.077%

    No Known Activations