© 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. 112970
    Prev
    Next
    INDEX
    Explanations

    government, agency, company, department 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
     forgiving
    -0.15
     demanding
    -0.14
     Forg
    -0.14
     demands
    -0.13
     compliment
    -0.12
     forg
    -0.12
     vocal
    -0.11
     forgive
    -0.11
     praising
    -0.11
     Claw
    -0.11
    POSITIVE LOGITS
     heed
    0.14
     balk
    0.14
     stubborn
    0.13
     accountable
    0.13
     responded
    0.13
     responds
    0.12
     respond
    0.12
     startled
    0.12
     response
    0.11
     responsiveness
    0.11
    Activations Density 0.183%

    No Known Activations