© 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. 25203
    Prev
    Next
    INDEX
    Explanations

    performance efficiency

    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
     stalking
    -0.09
    urent
    -0.08
    _printer
    -0.08
     plut
    -0.08
    dn
    -0.07
     AAC
    -0.07
    лÑİ
    -0.07
    DAL
    -0.07
     Redistributions
    -0.07
     richest
    -0.07
    POSITIVE LOGITS
     performance
    0.89
     Performance
    0.82
     performances
    0.79
    Performance
    0.76
    performance
    0.74
     PERFORMANCE
    0.68
     Perform
    0.68
    -performance
    0.67
     perform
    0.66
     performer
    0.63
    Activations Density 0.636%

    No Known Activations