© 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. 14706
    Prev
    Next
    INDEX
    Explanations

    school and graduates

    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
     Employees
    -0.09
     usur
    -0.09
    itti
    -0.09
    Employees
    -0.09
    hek
    -0.08
     moo
    -0.08
     employees
    -0.08
    employees
    -0.08
     Lawyer
    -0.08
     employee
    -0.08
    POSITIVE LOGITS
     instructors
    0.38
     instructor
    0.37
     Instructor
    0.33
     classmates
    0.31
     graduation
    0.27
    structors
    0.26
     graduating
    0.25
     trainers
    0.25
     graduates
    0.25
     students
    0.24
    Activations Density 0.601%

    No Known Activations