© 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. 15473
    Prev
    Next
    INDEX
    Explanations

    hiring and selection process

    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
     volunteered
    -0.13
     earn
    -0.11
     vol
    -0.11
     voluntary
    -0.11
    vol
    -0.11
     volunteering
    -0.11
     Earn
    -0.10
     earning
    -0.10
    Earn
    -0.10
     guessing
    -0.10
    POSITIVE LOGITS
     finalists
    0.16
     evaluating
    0.14
     interviewing
    0.14
     narrowed
    0.13
     Evalu
    0.13
     reviewing
    0.13
     liked
    0.12
     finalize
    0.12
     interviews
    0.12
     interviewed
    0.12
    Activations Density 0.373%

    No Known Activations