© 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. 3478
    Prev
    Next
    INDEX
    Explanations

    Chand names or Chanel

    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
    streams
    -0.10
    Ø®
    -0.09
     Merlin
    -0.08
    ivant
    -0.07
    dden
    -0.07
    mez
    -0.07
    antium
    -0.07
    -webpack
    -0.07
    ehler
    -0.07
    ientos
    -0.07
    POSITIVE LOGITS
    le
    0.15
    rika
    0.12
    /gallery
    0.12
    rase
    0.11
     coco
    0.11
    lers
    0.10
    rica
    0.10
    ocl
    0.10
    ece
    0.10
    asser
    0.10
    Activations Density 0.006%

    No Known Activations