© 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. 17444
    Prev
    Next
    INDEX
    Explanations

    political/military groups and their actions

    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
     backlog
    -0.09
     churn
    -0.09
    /company
    -0.09
     ration
    -0.08
     stagnant
    -0.08
     starving
    -0.08
     hectic
    -0.08
     incremental
    -0.08
     Incre
    -0.08
     trou
    -0.08
    POSITIVE LOGITS
     param
    0.13
     policing
    0.11
     recruits
    0.11
     Bride
    0.11
     opposed
    0.11
     oppose
    0.10
     extortion
    0.10
     power
    0.10
     opposes
    0.10
     influence
    0.10
    Activations Density 0.813%

    No Known Activations