© 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. 112604
    Prev
    Next
    INDEX
    Explanations

    agreement signed or between parties

    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
     rav
    -0.10
     reserved
    -0.10
    uko
    -0.09
     pai
    -0.09
     fuse
    -0.09
    éħį
    -0.09
    anced
    -0.09
    ëĭ
    -0.09
     throat
    -0.09
     advert
    -0.08
    POSITIVE LOGITS
     signed
    0.20
     Signed
    0.17
    /ag
    0.14
     agreement
    0.14
     signings
    0.14
    Signed
    0.14
    signed
    0.14
     governing
    0.14
     document
    0.13
     agreements
    0.13
    Activations Density 0.350%

    No Known Activations