© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89867
    Prev
    Next
    INDEX
    Explanations

    management structure and teams

    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
    grounds
    -0.10
    inox
    -0.09
    ances
    -0.09
    aro
    -0.09
    shed
    -0.09
    anko
    -0.09
    Flip
    -0.09
    ends
    -0.09
     Abel
    -0.09
    cxx
    -0.09
    POSITIVE LOGITS
    /admin
    0.16
    /Admin
    0.16
    /exec
    0.16
     structure
    0.14
    /mark
    0.13
     Structure
    0.13
     leadership
    0.12
     decisions
    0.12
    /board
    0.12
     positions
    0.12
    Activations Density 0.170%

    No Known Activations