© 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. 6723
    Prev
    Next
    INDEX
    Explanations

    job or employment

    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
    ooke
    -0.09
    otas
    -0.09
     expansion
    -0.09
    ühl
    -0.09
     Boyle
    -0.09
     Clem
    -0.09
    enic
    -0.09
    ULK
    -0.09
    .vaadin
    -0.09
     Surgical
    -0.09
    POSITIVE LOGITS
     jobs
    0.56
     job
    0.53
     employment
    0.50
     Jobs
    0.42
    jobs
    0.40
    job
    0.39
     Job
    0.38
    employment
    0.38
     Employment
    0.37
     JOB
    0.37
    Activations Density 0.422%

    No Known Activations