© 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. 88146
    Prev
    Next
    INDEX
    Explanations

    relationships, reconciliation, and comebacks

    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
    riba
    -0.11
     introdu
    -0.11
    richt
    -0.10
     nowrap
    -0.10
     jardin
    -0.10
     Leisure
    -0.10
     laz
    -0.09
     leisure
    -0.09
     Lazy
    -0.09
     preference
    -0.09
    POSITIVE LOGITS
     reconciliation
    0.34
     reunion
    0.27
     reun
    0.27
     breakup
    0.26
     reconc
    0.26
     reunited
    0.25
     reconnect
    0.23
     reconcile
    0.21
     reinst
    0.21
     comeback
    0.19
    Activations Density 0.124%

    No Known Activations