© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113653
    Prev
    Next
    INDEX
    Explanations

    both partners or either side

    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
    rap
    -0.08
     exempt
    -0.07
     Grant
    -0.07
     donation
    -0.07
     closely
    -0.07
    bite
    -0.07
     Rav
    -0.07
    iche
    -0.07
    _backend
    -0.07
     Rub
    -0.06
    POSITIVE LOGITS
     partner
    0.25
     partners
    0.25
     party
    0.22
     parties
    0.22
     participant
    0.21
     participants
    0.20
    partner
    0.19
     Partner
    0.19
    Partner
    0.17
     Partners
    0.17
    Activations Density 0.154%

    No Known Activations