© 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. 17663
    Prev
    Next
    INDEX
    Explanations

    government/sports teams were defeated/lost

    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
     enjoying
    -0.11
     sympathetic
    -0.11
     sympathy
    -0.11
     gigg
    -0.11
     adore
    -0.10
     subscribed
    -0.10
     eup
    -0.10
     rupt
    -0.10
     gratitude
    -0.10
    joy
    -0.09
    POSITIVE LOGITS
     tried
    0.18
     protests
    0.17
     powerless
    0.16
     tries
    0.16
     attempted
    0.16
     protested
    0.16
     Try
    0.16
     futile
    0.16
     attempts
    0.16
     protest
    0.16
    Activations Density 0.047%

    No Known Activations