© 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. 111767
    Prev
    Next
    INDEX
    Explanations

    board of directors or trustees

    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
     debunk
    -0.12
     Cler
    -0.10
     consul
    -0.10
    acro
    -0.10
     HQ
    -0.10
     office
    -0.10
    leader
    -0.10
     Coordinator
    -0.09
     headquarters
    -0.09
     residence
    -0.09
    POSITIVE LOGITS
     board
    0.24
     trustees
    0.20
     directors
    0.20
     Trustees
    0.20
     Board
    0.20
     boards
    0.19
    Board
    0.18
     Directors
    0.15
    -board
    0.15
     Boards
    0.14
    Activations Density 0.356%

    No Known Activations