© 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. 111415
    Prev
    Next
    INDEX
    Explanations

    task of 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
     Dud
    -0.10
    kal
    -0.09
    chet
    -0.09
    ryn
    -0.09
    undi
    -0.09
    Sac
    -0.09
    thin
    -0.09
     Tobacco
    -0.08
    agit
    -0.08
     Dalton
    -0.08
    POSITIVE LOGITS
     task
    0.26
     tasks
    0.17
    task
    0.17
     Task
    0.16
    Task
    0.16
    -task
    0.15
     tasked
    0.15
    ä»»åĬ¡
    0.15
     daunting
    0.13
     tedious
    0.13
    Activations Density 0.105%

    No Known Activations