© 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. 91701
    Prev
    Next
    INDEX
    Explanations

    education and training

    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
    kus
    -0.10
     humming
    -0.10
     empt
    -0.10
     smelling
    -0.09
     rocking
    -0.09
     previous
    -0.09
     success
    -0.09
     worldly
    -0.08
     selfies
    -0.08
     typed
    -0.08
    POSITIVE LOGITS
     education
    0.19
     educating
    0.17
     training
    0.16
     outreach
    0.16
    education
    0.16
     dissemination
    0.15
     collaborations
    0.15
     partnerships
    0.15
     educate
    0.14
     Education
    0.14
    Activations Density 4.614%

    No Known Activations