© 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. 30644
    Prev
    Next
    INDEX
    Explanations

    tariffs and trade 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
     Exhaust
    -0.10
    fc
    -0.10
     Terminator
    -0.10
     FC
    -0.09
     кли
    -0.09
    685
    -0.09
    Addon
    -0.09
     indic
    -0.09
    elden
    -0.09
     internally
    -0.09
    POSITIVE LOGITS
     fairness
    0.23
     unfair
    0.19
     fair
    0.19
     retali
    0.19
     recipro
    0.19
     Fair
    0.18
     retaliation
    0.18
     symmetry
    0.18
     tit
    0.17
     equality
    0.17
    Activations Density 0.084%

    No Known Activations