© 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. 115877
    Prev
    Next
    INDEX
    Explanations

    official titles and positions

    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
     Britann
    -0.11
     undefeated
    -0.11
     resale
    -0.10
     sla
    -0.10
     contractual
    -0.10
     cheated
    -0.10
     apprent
    -0.10
     boarding
    -0.10
     renting
    -0.10
    Sibling
    -0.09
    POSITIVE LOGITS
     deputy
    0.21
     secretary
    0.21
     Secretary
    0.21
     Deputy
    0.20
     Provincial
    0.17
    Secretary
    0.17
     deputies
    0.17
     minister
    0.16
     office
    0.16
     provincial
    0.16
    Activations Density 0.149%

    No Known Activations