© 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. 47861
    Prev
    Next
    INDEX
    Explanations

    changing laws or policies

    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
     intend
    -0.11
     Compliance
    -0.10
     Braz
    -0.09
     unders
    -0.09
    /respond
    -0.09
     poster
    -0.09
     spiel
    -0.09
     injuring
    -0.09
     bedding
    -0.08
     overd
    -0.08
    POSITIVE LOGITS
     reform
    0.17
     repeal
    0.16
     reinst
    0.15
     ban
    0.15
     overhaul
    0.14
     reforms
    0.14
     abol
    0.14
     universal
    0.14
     resurrect
    0.14
     revive
    0.14
    Activations Density 1.749%

    No Known Activations