© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    sale, sell, or selling

    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
     Remed
    -0.10
     retrie
    -0.10
     Retrie
    -0.10
     Disaster
    -0.10
    Budget
    -0.10
     remed
    -0.09
    visa
    -0.09
     retrieved
    -0.09
     Reward
    -0.09
     whistleblower
    -0.09
    POSITIVE LOGITS
     selling
    0.75
     sell
    0.72
     sale
    0.71
     sales
    0.66
     Selling
    0.66
     sold
    0.66
     sells
    0.64
     Sell
    0.61
     Sales
    0.57
     Sale
    0.57
    Activations Density 0.460%

    No Known Activations