© 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. 26542
    Prev
    Next
    INDEX
    Explanations

    promotion and career advancement

    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
     undef
    -0.10
     Fant
    -0.09
     bulk
    -0.09
     unarmed
    -0.09
     rag
    -0.09
    rag
    -0.09
     daily
    -0.09
    igm
    -0.09
     Surre
    -0.09
     Defender
    -0.09
    POSITIVE LOGITS
     promotion
    0.38
     promotions
    0.37
     advancement
    0.34
     career
    0.33
     Promotion
    0.32
     promot
    0.31
    promotion
    0.29
     promoted
    0.28
     Career
    0.27
     climb
    0.27
    Activations Density 0.328%

    No Known Activations