© 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. 112960
    Prev
    Next
    INDEX
    Explanations

    societal trends and changes

    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
     unspecified
    -0.11
     undisclosed
    -0.11
     instantly
    -0.11
     requesting
    -0.11
     afterwards
    -0.11
     personally
    -0.10
     immediately
    -0.10
     verbally
    -0.10
     Normally
    -0.10
     automatically
    -0.09
    POSITIVE LOGITS
     widespread
    0.23
     trends
    0.23
     mainstream
    0.22
     worldwide
    0.22
     globalization
    0.21
     historically
    0.21
     societal
    0.20
     nowadays
    0.20
     Trends
    0.19
     today
    0.19
    Activations Density 0.467%

    No Known Activations