© 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. 8229
    Prev
    Next
    INDEX
    Explanations

    weekly series or monthly series

    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
     sunk
    -0.12
     Consolid
    -0.11
     Blink
    -0.11
    ChangeEvent
    -0.11
     duplic
    -0.11
     Dou
    -0.11
    blink
    -0.11
    roups
    -0.11
     Registr
    -0.10
     Sever
    -0.10
    POSITIVE LOGITS
     series
    0.38
     Series
    0.29
    series
    0.29
    -series
    0.27
    Series
    0.27
     SERIES
    0.26
     serie
    0.24
     weekly
    0.23
    _series
    0.22
     monthly
    0.21
    Activations Density 0.841%

    No Known Activations