© 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. 50799
    Prev
    Next
    INDEX
    Explanations

    number followed by of, one, or formatting

    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
    æķ°
    -0.11
     numbers
    -0.11
     sá»ij
    -0.10
     number
    -0.10
    simp
    -0.10
    avic
    -0.10
    IED
    -0.10
    ut
    -0.10
    uga
    -0.10
    ست
    -0.10
    POSITIVE LOGITS
    째
    0.17
     crunch
    0.13
     plate
    0.12
    ical
    0.12
    FormatException
    0.11
     noqa
    0.11
    plate
    0.11
     Crunch
    0.11
    çłģ
    0.10
    SBATCH
    0.10
    Activations Density 0.489%

    No Known Activations