© 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. 87854
    Prev
    Next
    INDEX
    Explanations

    defense, government, ministry, intelligence, secretary

    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
    sta
    -0.10
    cales
    -0.10
    translated
    -0.09
    lio
    -0.09
    >window
    -0.09
    cke
    -0.09
    uchar
    -0.09
    iability
    -0.09
     Bulg
    -0.09
    oader
    -0.09
    POSITIVE LOGITS
     minister
    0.19
     Minister
    0.18
     ministry
    0.17
     Ministry
    0.17
     ministries
    0.15
    lessness
    0.15
    less
    0.15
     mechanism
    0.15
     ministers
    0.15
    lessly
    0.14
    Activations Density 0.050%

    No Known Activations