© 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. 46122
    Prev
    Next
    INDEX
    Explanations

    clear, easy, obvious

    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
     prefect
    -0.08
     subs
    -0.08
    aran
    -0.08
     supp
    -0.08
     routine
    -0.08
    cons
    -0.08
    -cons
    -0.08
     reluctant
    -0.08
    vida
    -0.08
    cec
    -0.08
    POSITIVE LOGITS
     needless
    0.14
     Needless
    0.12
    epam
    0.11
     testament
    0.11
     Atl
    0.11
     imb
    0.11
     Plain
    0.11
     obviously
    0.11
     unmistak
    0.11
     certainty
    0.10
    Activations Density 0.002%

    No Known Activations