© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    license or source information

    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
    iske
    -0.08
     Washer
    -0.08
     Compass
    -0.07
     Spacer
    -0.07
     conven
    -0.07
    .HttpServlet
    -0.07
    acf
    -0.07
    positor
    -0.07
    FLASH
    -0.07
    404
    -0.06
    POSITIVE LOGITS
    SourceType
    0.15
    sink
    0.11
     sinks
    0.11
    .Cancel
    0.11
     destination
    0.10
    _medium
    0.10
    .DataBind
    0.10
     traceback
    0.10
    /catalog
    0.10
     sink
    0.10
    Activations Density 0.966%

    No Known Activations