© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    read

    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
     Colbert
    -0.10
    unal
    -0.09
     Aren
    -0.09
    bic
    -0.09
    kok
    -0.09
     Ricardo
    -0.08
     Wiley
    -0.08
     ambit
    -0.08
    anim
    -0.08
     Slate
    -0.08
    POSITIVE LOGITS
    read
    0.13
     read
    0.10
    (read
    0.10
    -read
    0.10
    âĢ¦”↵↵
    0.09
     [...]↵↵
    0.09
    âĢ¦”
    0.09
     Read
    0.09
     [...
    0.09
    ......↵↵
    0.09
    Activations Density 0.335%

    No Known Activations