© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92276
    Prev
    Next
    INDEX
    Explanations

    secret society mission intelligence

    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
     faithfully
    -0.09
    rib
    -0.09
    ieber
    -0.09
    kart
    -0.09
     Transparent
    -0.09
     Spirits
    -0.09
     Hearth
    -0.09
     Novel
    -0.09
     thought
    -0.09
     probing
    -0.09
    POSITIVE LOGITS
     gem
    0.12
     handshake
    0.12
     tucked
    0.11
     gems
    0.11
     underground
    0.11
     thriving
    0.10
     hidden
    0.10
     Wal
    0.10
     Bras
    0.09
     circulating
    0.09
    Activations Density 0.009%

    No Known Activations