© 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. 117408
    Prev
    Next
    INDEX
    Explanations

    playing or doing something

    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
     Enlight
    -0.11
     Shr
    -0.11
     enlightened
    -0.10
     Hobby
    -0.09
     illumin
    -0.09
     illum
    -0.09
     Wor
    -0.09
     Werk
    -0.09
    chine
    -0.09
    eres
    -0.08
    POSITIVE LOGITS
     around
    0.20
     with
    0.16
     about
    0.15
     Around
    0.13
    around
    0.13
     together
    0.12
    /chat
    0.12
     among
    0.12
    -around
    0.11
    with
    0.11
    Activations Density 0.038%

    No Known Activations