© 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. 15077
    Prev
    Next
    INDEX
    Explanations

    career / careers

    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
     Shib
    -0.12
    immers
    -0.10
    社
    -0.10
     Ranch
    -0.10
     everyday
    -0.09
    otti
    -0.09
     bond
    -0.08
     Rem
    -0.08
    zman
    -0.08
    DG
    -0.08
    POSITIVE LOGITS
     career
    0.58
     careers
    0.48
     Career
    0.47
    career
    0.43
    Career
    0.42
     Careers
    0.39
     early
    0.27
     professional
    0.25
     professionally
    0.24
    -care
    0.22
    Activations Density 0.748%

    No Known Activations