© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18723
    Prev
    Next
    INDEX
    Explanations

    rubbed his eyes

    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
    Negative Logits
     unm
    -0.12
     cunning
    -0.12
     gigg
    -0.10
    adro
    -0.10
     injust
    -0.10
    ajas
    -0.10
     Sed
    -0.10
     Cunning
    -0.10
     satisfied
    -0.09
     Tube
    -0.09
    POSITIVE LOGITS
     headache
    0.23
     rub
    0.21
     rubbed
    0.18
     headaches
    0.18
     stress
    0.18
     rubbing
    0.17
     Stress
    0.16
     stressful
    0.16
    rub
    0.16
     migraine
    0.16
    Activations Density 0.064%

    No Known Activations