© 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. 3967
    Prev
    Next
    INDEX
    Explanations

    teacher positions

    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
     entrepreneur
    -0.11
     Businesses
    -0.10
    Ìģ
    -0.10
     operatives
    -0.10
     Entrepreneur
    -0.10
     Merchant
    -0.10
     CEOs
    -0.10
     Ivanka
    -0.09
    .inc
    -0.09
     Commander
    -0.09
    POSITIVE LOGITS
     teacher
    0.40
     teachers
    0.39
     Teacher
    0.38
     teaching
    0.37
     Teachers
    0.36
    Teachers
    0.34
     Teaching
    0.33
    teacher
    0.33
    Teacher
    0.32
    teachers
    0.32
    Activations Density 0.776%

    No Known Activations