© 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. 114769
    Prev
    Next
    INDEX
    Explanations

    legal and financial 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
     firstly
    -0.10
     Gran
    -0.09
     Aquarium
    -0.09
     Rich
    -0.09
     anticipation
    -0.09
    vim
    -0.08
     reminding
    -0.08
     Preparation
    -0.08
     policymakers
    -0.08
     preparation
    -0.08
    POSITIVE LOGITS
     pension
    0.19
     patent
    0.19
     extradition
    0.17
     loan
    0.17
     taxes
    0.17
     visas
    0.17
     tax
    0.17
     copyright
    0.16
     pensions
    0.16
     parole
    0.16
    Activations Density 1.580%

    No Known Activations