© 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. 50509
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by question or new thought

    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
     moreover
    -0.11
    .but
    -0.11
    .And
    -0.10
     Meanwhile
    -0.10
    Meanwhile
    -0.10
     infinitely
    -0.09
     sac
    -0.09
    .That
    -0.09
    Otherwise
    -0.09
     Zag
    -0.09
    POSITIVE LOGITS
     why
    0.17
    why
    0.15
     if
    0.15
     beware
    0.14
     Why
    0.14
     If
    0.14
     WHY
    0.13
    :
    0.13
    If
    0.13
     since
    0.13
    Activations Density 0.139%

    No Known Activations