© 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. 92365
    Prev
    Next
    INDEX
    Explanations

    circumference and diameter

    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
     Consolid
    -0.13
     beside
    -0.12
     selfish
    -0.12
     newcom
    -0.12
     enthusi
    -0.11
     oblivious
    -0.11
     whispers
    -0.11
     desper
    -0.11
     prag
    -0.11
     Bes
    -0.11
    POSITIVE LOGITS
     circumference
    0.12
     diameter
    0.10
     evenly
    0.10
     tip
    0.10
     intact
    0.10
     insertion
    0.10
     circumcision
    0.10
     widest
    0.10
     portion
    0.10
     expansion
    0.09
    Activations Density 0.003%

    No Known Activations