© 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. 28758
    Prev
    Next
    INDEX
    Explanations

    deal, swap, bargain

    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
    alue
    -0.11
    çģ
    -0.11
     Sims
    -0.10
     urge
    -0.10
     wrapping
    -0.10
    sten
    -0.10
     Express
    -0.10
    stu
    -0.10
     polit
    -0.10
     rapp
    -0.10
    POSITIVE LOGITS
     deal
    0.28
     bargain
    0.26
     Deal
    0.26
    Deal
    0.25
     agreement
    0.24
     barg
    0.22
     fair
    0.21
     bargaining
    0.20
     terms
    0.20
     agreed
    0.19
    Activations Density 0.076%

    No Known Activations