© 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. 15159
    Prev
    Next
    INDEX
    Explanations

    historical figures and time periods

    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
     unveiled
    -0.10
     Mick
    -0.10
     uncovered
    -0.10
    vertiser
    -0.10
     standby
    -0.10
     Dust
    -0.10
     dusty
    -0.10
     dust
    -0.10
     cracking
    -0.10
    ény
    -0.10
    POSITIVE LOGITS
     contempor
    0.14
     contemporary
    0.12
     Likely
    0.11
    likely
    0.11
     likely
    0.11
     corrobor
    0.11
     Tac
    0.11
     Caesar
    0.11
     chron
    0.11
    opy
    0.11
    Activations Density 0.872%

    No Known Activations