© 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. 3668
    Prev
    Next
    INDEX
    Explanations

    money and spending

    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
     prov
    -0.12
     Wilderness
    -0.10
     diluted
    -0.10
     provid
    -0.10
     Lomb
    -0.09
     Pen
    -0.09
     Serve
    -0.09
    oub
    -0.08
     Luck
    -0.08
     sais
    -0.08
    POSITIVE LOGITS
     budget
    0.48
     budgets
    0.44
     Budget
    0.41
    Budget
    0.39
    budget
    0.39
    -budget
    0.34
    _budget
    0.30
     spending
    0.23
    udget
    0.22
     willing
    0.21
    Activations Density 0.096%

    No Known Activations