© 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. 91652
    Prev
    Next
    INDEX
    Explanations

    profession duties and salary

    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
     block
    -0.10
     ancestral
    -0.09
    blocking
    -0.09
    antically
    -0.09
     lineup
    -0.09
     reinforcing
    -0.09
     Block
    -0.08
     repetitions
    -0.08
    indicator
    -0.08
     boasting
    -0.08
    POSITIVE LOGITS
     duties
    0.21
     typical
    0.19
     salary
    0.18
     Dut
    0.17
     salaries
    0.17
     Typical
    0.17
     responsibilities
    0.17
    typ
    0.17
     profession
    0.17
     careers
    0.17
    Activations Density 0.122%

    No Known Activations