© 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. 26304
    Prev
    Next
    INDEX
    Explanations

    in everybody / our / the / each / allied

    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
     overl
    -0.09
     temporal
    -0.09
    ahl
    -0.09
     Armen
    -0.08
     strang
    -0.08
    oth
    -0.08
     comport
    -0.08
     redundant
    -0.08
     Kosten
    -0.08
     syll
    -0.08
    POSITIVE LOGITS
     attendance
    0.14
     populate
    0.12
     positions
    0.12
     workforce
    0.12
     society
    0.12
    ociety
    0.12
     circulation
    0.11
     Attendance
    0.11
     nowadays
    0.11
     themselves
    0.11
    Activations Density 0.190%

    No Known Activations