© 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. 27310
    Prev
    Next
    INDEX
    Explanations

    either one or either/or

    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
     Bien
    -0.11
    ches
    -0.10
    eki
    -0.10
     bas
    -0.09
     nth
    -0.09
    pretty
    -0.09
     Kerry
    -0.09
    Divider
    -0.09
    roups
    -0.09
    acas
    -0.08
    POSITIVE LOGITS
     either
    0.30
     one
    0.29
     EITHER
    0.28
     Either
    0.27
    Either
    0.24
    either
    0.23
     ONE
    0.20
     whichever
    0.19
     One
    0.18
    _one
    0.17
    Activations Density 0.157%

    No Known Activations