© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6864
    Prev
    Next
    INDEX
    Explanations

    foreign policy, language, key, exchange

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¡
    -0.09
    isman
    -0.09
    acious
    -0.09
    zt
    -0.08
    plet
    -0.08
    etten
    -0.08
    mare
    -0.08
    izon
    -0.08
    ongs
    -0.08
    imed
    -0.08
    POSITIVE LOGITS
    er
    0.24
    ness
    0.16
    -language
    0.15
    -born
    0.15
    -policy
    0.14
     nationals
    0.14
     Affairs
    0.14
     exchange
    0.13
     affairs
    0.13
    ers
    0.12
    Activations Density 0.035%

    No Known Activations