© 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. 18769
    Prev
    Next
    INDEX
    Explanations

    Poland

    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
    acom
    -0.09
    agy
    -0.09
    iles
    -0.08
    .jp
    -0.08
     affection
    -0.08
    agu
    -0.08
    agi
    -0.08
    ensch
    -0.08
    achten
    -0.08
    oro
    -0.08
    POSITIVE LOGITS
    ynomials
    0.13
     polished
    0.13
     Damascus
    0.12
    ÑĤоÑĢ
    0.11
    Pol
    0.11
     Poland
    0.11
     polled
    0.11
     Polish
    0.10
    ished
    0.10
     pol
    0.10
    Activations Density 0.060%

    No Known Activations