© 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. 8139
    Prev
    Next
    INDEX
    Explanations

    Luke followed by names

    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
    orta
    -0.10
    ousse
    -0.10
    iot
    -0.10
     Odd
    -0.09
    ester
    -0.09
    essed
    -0.09
     OSX
    -0.08
     unh
    -0.08
    xon
    -0.08
          ↵      ↵
    -0.08
    POSITIVE LOGITS
     Skywalker
    0.16
     sky
    0.09
    istics
    0.09
    fall
    0.09
     warm
    0.08
    prog
    0.08
     Nicht
    0.08
     Cage
    0.08
     imperial
    0.08
    alysis
    0.08
    Activations Density 0.030%

    No Known Activations