© 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. 6522
    Prev
    Next
    INDEX
    Explanations

    studied academic disciplines

    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
    cov
    -0.08
     forts
    -0.08
     departments
    -0.07
     contingent
    -0.07
     Elias
    -0.07
     dawn
    -0.07
    ear
    -0.07
     compliment
    -0.07
    ivia
    -0.07
     Departments
    -0.07
    POSITIVE LOGITS
     abroad
    0.20
     medicine
    0.16
     journalism
    0.15
     theology
    0.14
     psychology
    0.14
     philosophy
    0.14
     diligently
    0.13
     sociology
    0.13
     economics
    0.13
     classics
    0.13
    Activations Density 0.109%

    No Known Activations