© 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. 117012
    Prev
    Next
    INDEX
    Explanations

    chain of command or chain reaction

    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
    apan
    -0.08
    .chapter
    -0.08
    vro
    -0.08
    inish
    -0.08
     tray
    -0.07
     Marcus
    -0.07
     trajectories
    -0.07
    asz
    -0.07
     ',',
    -0.07
     Gavin
    -0.07
    POSITIVE LOGITS
    .Chain
    0.18
     chain
    0.17
     Chain
    0.17
    chain
    0.15
    -chain
    0.15
     reaction
    0.15
    CHAIN
    0.15
    Chain
    0.14
    (chain
    0.14
    reaction
    0.13
    Activations Density 0.075%

    No Known Activations