© 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. 92594
    Prev
    Next
    INDEX
    Explanations

    new examples, types, insights, methods, knowledge

    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
    fx
    -0.10
     Griffith
    -0.09
     Kramer
    -0.09
    Removed
    -0.09
     experience
    -0.09
    lr
    -0.09
     Stout
    -0.09
     Removed
    -0.09
    experience
    -0.09
     Lawson
    -0.09
    POSITIVE LOGITS
    /new
    0.16
    /add
    0.16
     technologies
    0.12
     developments
    0.11
    /im
    0.11
     Features
    0.11
    /rest
    0.10
     appoint
    0.10
    /en
    0.10
     Parad
    0.10
    Activations Density 0.540%

    No Known Activations