© 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. 5968
    Prev
    Next
    INDEX
    Explanations

    either their / they were

    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
     itself
    -0.11
    cape
    -0.10
     its
    -0.09
     коÑĤоÑĢÑĭй
    -0.09
     Its
    -0.09
    ä¸Ģ个
    -0.09
     someone
    -0.09
    eln
    -0.09
     two
    -0.09
     famously
    -0.09
    POSITIVE LOGITS
     either
    0.29
    either
    0.24
     themselves
    0.24
     Either
    0.23
    Either
    0.22
     varying
    0.19
     sometimes
    0.19
     often
    0.18
     their
    0.18
     various
    0.18
    Activations Density 0.738%

    No Known Activations