© 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. 89721
    Prev
    Next
    INDEX
    Explanations

    I have recently

    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
     already
    -0.11
     duly
    -0.09
    already
    -0.09
    preced
    -0.09
    Already
    -0.09
     preced
    -0.09
     Already
    -0.09
     Activity
    -0.09
     stip
    -0.09
     chosen
    -0.09
    POSITIVE LOGITS
     awhile
    0.13
     occasionally
    0.13
     recently
    0.13
     occasional
    0.12
    recent
    0.12
     intermitt
    0.12
     nicknamed
    0.11
     recent
    0.11
     briefly
    0.11
     sometime
    0.11
    Activations Density 0.127%

    No Known Activations