© 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. 3718
    Prev
    Next
    INDEX
    Explanations

    decide what to

    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
     McCabe
    -0.11
    309
    -0.11
    ordered
    -0.11
    IDO
    -0.10
    localized
    -0.10
     Ranking
    -0.10
     Harvey
    -0.10
    jur
    -0.10
     Rankings
    -0.10
    eden
    -0.10
    POSITIVE LOGITS
     prices
    0.16
     freely
    0.13
     rates
    0.13
     Decide
    0.13
     decide
    0.13
     decides
    0.13
     Prices
    0.12
     price
    0.12
     whatever
    0.12
     pricing
    0.11
    Activations Density 0.008%

    No Known Activations