© 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. 50541
    Prev
    Next
    INDEX
    Explanations

    engineering, maintenance, and officer roles

    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
    -inspired
    -0.11
    FUL
    -0.11
    venture
    -0.11
     avent
    -0.11
    -themed
    -0.10
     Carb
    -0.10
    -aff
    -0.10
    -ind
    -0.10
    -like
    -0.10
    mine
    -0.10
    POSITIVE LOGITS
     duties
    0.20
     department
    0.18
     technicians
    0.16
     duty
    0.16
    åijĺ
    0.15
     crew
    0.15
     technician
    0.15
     staff
    0.15
     team
    0.14
     chores
    0.14
    Activations Density 1.164%

    No Known Activations