© 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. 16387
    Prev
    Next
    INDEX
    Explanations

    sit or seating

    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
     Ves
    -0.10
    yal
    -0.09
     Ivory
    -0.09
     vets
    -0.09
    LBL
    -0.09
    (END
    -0.09
     observ
    -0.08
     unfit
    -0.08
    222
    -0.08
     nets
    -0.08
    POSITIVE LOGITS
     sit
    0.37
     seated
    0.33
     Sit
    0.31
    Sit
    0.31
     seat
    0.30
     seating
    0.29
    sit
    0.29
     seats
    0.28
     sits
    0.28
     sitting
    0.27
    Activations Density 0.103%

    No Known Activations