© 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. 88490
    Prev
    Next
    INDEX
    Explanations

    anthropology, sociology, linguistic studies

    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
     remix
    -0.10
     coaching
    -0.10
    STEM
    -0.10
     Photon
    -0.10
     resent
    -0.10
    ommen
    -0.09
     commercial
    -0.09
     Reb
    -0.09
     poll
    -0.09
    MD
    -0.09
    POSITIVE LOGITS
     ethn
    0.37
     anthropology
    0.33
     anthrop
    0.32
     Anthrop
    0.29
    Anth
    0.21
     eth
    0.19
    anth
    0.18
     Eth
    0.18
     sociology
    0.16
     soci
    0.16
    Activations Density 0.577%

    No Known Activations