© 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. 4747
    Prev
    Next
    INDEX
    Explanations

    negotiating terms and deals

    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
     calculations
    -0.14
    ropp
    -0.13
     laughing
    -0.11
    uche
    -0.10
     rejo
    -0.10
     preparations
    -0.10
     computations
    -0.10
     propensity
    -0.10
     shuffled
    -0.10
     Judgment
    -0.10
    POSITIVE LOGITS
     barg
    0.11
     compromise
    0.10
     behalf
    0.10
     bri
    0.10
     terms
    0.09
     fav
    0.09
     contracts
    0.09
     bais
    0.09
     discounts
    0.09
     comprom
    0.09
    Activations Density 0.058%

    No Known Activations