© 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. 92507
    Prev
    Next
    INDEX
    Explanations

    design and production

    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
    iki
    -0.08
     Blake
    -0.08
    edo
    -0.08
    avi
    -0.08
     Davidson
    -0.07
     Blaze
    -0.07
    isma
    -0.07
    hex
    -0.07
    fdc
    -0.07
    enberg
    -0.07
    POSITIVE LOGITS
     structure
    0.16
     physiology
    0.14
     philosophy
    0.14
     mechanics
    0.13
     execution
    0.13
     wording
    0.13
     design
    0.12
     Structure
    0.12
     style
    0.12
     terminology
    0.12
    Activations Density 0.628%

    No Known Activations