© 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. 32518
    Prev
    Next
    INDEX
    Explanations

    literacy education schooling educated

    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
     internship
    -0.11
     interns
    -0.10
     Intern
    -0.10
     psych
    -0.10
     inhabited
    -0.09
    ester
    -0.09
     APA
    -0.09
     Psych
    -0.09
    kon
    -0.09
    bz
    -0.09
    POSITIVE LOGITS
     literacy
    0.40
     education
    0.38
     Education
    0.33
     schooling
    0.33
    education
    0.32
    Education
    0.30
     educated
    0.29
     liter
    0.29
     educational
    0.29
     Liter
    0.28
    Activations Density 0.460%

    No Known Activations