© 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. 112554
    Prev
    Next
    INDEX
    Explanations

    teachers and instructors

    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
     backstage
    -0.10
     workstation
    -0.10
    pard
    -0.09
    ICY
    -0.09
    Executive
    -0.09
     colleg
    -0.08
     Jud
    -0.08
     colleague
    -0.08
     Executive
    -0.08
     debugging
    -0.08
    POSITIVE LOGITS
     teachers
    0.26
     teacher
    0.23
     Teachers
    0.20
    teachers
    0.19
    Teachers
    0.18
     instructors
    0.18
     Teacher
    0.18
    teacher
    0.17
    Teacher
    0.16
     instructor
    0.15
    Activations Density 0.278%

    No Known Activations