© 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. 92605
    Prev
    Next
    INDEX
    Explanations

    image copyright notices

    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
    wie
    -0.08
     ach
    -0.08
     quoting
    -0.08
     Poster
    -0.08
     quoted
    -0.08
     quotation
    -0.08
     wis
    -0.07
     pos
    -0.07
     resp
    -0.07
     redis
    -0.07
    POSITIVE LOGITS
     edited
    0.15
     blurred
    0.14
     anonym
    0.14
     professionally
    0.14
     dated
    0.13
     authentic
    0.13
     recent
    0.13
     blurry
    0.13
     sanitized
    0.13
     outdated
    0.13
    Activations Density 0.026%

    No Known Activations