© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    administration of services

    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
    unpack
    -0.10
     surg
    -0.10
     recognised
    -0.09
     fou
    -0.09
     UN
    -0.09
    _-
    -0.09
    successfully
    -0.09
    angling
    -0.09
    hear
    -0.09
     recognized
    -0.09
    POSITIVE LOGITS
     administered
    0.15
     received
    0.15
    received
    0.14
     delivered
    0.13
     treatment
    0.13
     deserved
    0.12
     Received
    0.12
     recieved
    0.12
     session
    0.12
     reception
    0.11
    Activations Density 0.068%

    No Known Activations