© 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. 27091
    Prev
    Next
    INDEX
    Explanations

    sow, reap, seed, wreak, wrought

    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
     possession
    -0.09
     dumb
    -0.09
    ERM
    -0.08
    zd
    -0.08
     efficacy
    -0.08
     rational
    -0.08
    ules
    -0.08
    ASM
    -0.08
     cancelling
    -0.08
    Placeholder
    -0.08
    POSITIVE LOGITS
     discord
    0.20
     seeds
    0.16
     sow
    0.15
    discord
    0.14
     Seeds
    0.14
     windy
    0.13
     Discord
    0.13
     whirl
    0.12
     confusion
    0.12
     oats
    0.12
    Activations Density 0.006%

    No Known Activations