© 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. 92364
    Prev
    Next
    INDEX
    Explanations

    successful performance

    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
    plib
    -0.12
     lump
    -0.11
    istani
    -0.11
     hitch
    -0.10
     uranus
    -0.10
    orbit
    -0.10
     coherence
    -0.10
    onso
    -0.10
    chief
    -0.10
     naked
    -0.10
    POSITIVE LOGITS
     successfully
    0.15
     confidently
    0.13
    successfully
    0.12
     smoothly
    0.12
     Successfully
    0.11
     trium
    0.11
     cleanly
    0.11
     victorious
    0.11
     exhilar
    0.11
     competitor
    0.10
    Activations Density 0.063%

    No Known Activations