© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29712
    Prev
    Next
    INDEX
    Explanations

    woke up and

    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
     sleep
    -0.16
     bed
    -0.15
    Sleep
    -0.15
     bedtime
    -0.14
     sleeps
    -0.14
     sleeping
    -0.14
     mornings
    -0.14
     slept
    -0.13
     Sleeping
    -0.13
    .sleep
    -0.13
    POSITIVE LOGITS
     downstairs
    0.12
     stumble
    0.12
     bathroom
    0.11
     activated
    0.11
     immediately
    0.11
     stumbling
    0.10
     immedi
    0.10
    otos
    0.10
    JE
    0.09
     activate
    0.09
    Activations Density 0.062%

    No Known Activations