© 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. 116997
    Prev
    Next
    INDEX
    Explanations

    to be or to date

    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
    ella
    -0.10
    ELY
    -0.09
     Glover
    -0.09
    ér
    -0.09
     medi
    -0.09
    arez
    -0.09
     Undo
    -0.09
    ि
    -0.09
    inet
    -0.09
    akin
    -0.09
    POSITIVE LOGITS
     emerge
    0.17
     grace
    0.15
     ever
    0.14
     emerged
    0.13
     emerges
    0.13
     arise
    0.12
     arrive
    0.11
     come
    0.11
    ever
    0.11
     successfully
    0.11
    Activations Density 0.079%

    No Known Activations