© 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. 111691
    Prev
    Next
    INDEX
    Explanations

    sequences of digits

    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
    Not in Any Lists

    No Comments

    Negative Logits
     mono
    -0.10
     po
    -0.10
    mono
    -0.10
    cola
    -0.09
     renamed
    -0.09
     cwd
    -0.09
     Po
    -0.09
     Stap
    -0.09
     cruc
    -0.09
     Watt
    -0.09
    POSITIVE LOGITS
     digits
    0.34
    Digits
    0.27
    -digit
    0.23
     digit
    0.23
    digits
    0.22
     numbers
    0.22
     codes
    0.22
    _digits
    0.22
     prefixes
    0.21
     prefix
    0.21
    Activations Density 1.523%

    No Known Activations