© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15853
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    /feed
    -0.11
     punishment
    -0.10
     Feed
    -0.09
     punishments
    -0.08
     punitive
    -0.08
     feed
    -0.08
     stringify
    -0.08
     fed
    -0.08
     humiliating
    -0.08
    lesson
    -0.08
    POSITIVE LOGITS
     Passenger
    0.10
     eclips
    0.10
    ichert
    0.10
     Hancock
    0.10
     datap
    0.10
     Beacon
    0.09
     amor
    0.09
     “âĢ¦
    0.09
     datab
    0.09
     sperm
    0.09
    Activations Density 0.018%

    No Known Activations