© 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. 3509
    Prev
    Next
    INDEX
    Explanations

    sole purpose, responsibility, or exclusive interest

    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
    ets
    -0.12
    eer
    -0.12
    reme
    -0.11
    ella
    -0.10
    sono
    -0.10
    role
    -0.10
    etz
    -0.10
    loo
    -0.10
    erro
    -0.09
    ات
    -0.09
    POSITIVE LOGITS
     proprietor
    0.15
    mn
    0.15
     purpose
    0.13
     discretion
    0.13
    -purpose
    0.11
     responsibility
    0.11
     Purpose
    0.11
    -authored
    0.11
     propriet
    0.11
    purpose
    0.11
    Activations Density 0.017%

    No Known Activations