© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92379
    Prev
    Next
    INDEX
    Explanations

    Italy, jazz, dad, steroidal

    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
    Negative Logits
     surely
    -0.12
     Gee
    -0.11
     IMO
    -0.11
     WTF
    -0.10
    lad
    -0.10
     fé
    -0.10
     sickness
    -0.10
     succeed
    -0.10
     Surely
    -0.10
     positively
    -0.10
    POSITIVE LOGITS
     basically
    0.14
     actually
    0.14
     essentially
    0.12
    actually
    0.12
     Basically
    0.12
     gentleman
    0.11
     Actually
    0.11
    Basically
    0.11
    —we
    0.11
    âĢ¦and
    0.10
    Activations Density 0.291%

    No Known Activations