© 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. 50706
    Prev
    Next
    INDEX
    Explanations

    view or purpose

    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
    quot
    -0.11
    isse
    -0.10
     Maid
    -0.10
    ourg
    -0.10
     joys
    -0.10
    esse
    -0.09
     nic
    -0.09
     Orr
    -0.09
    ades
    -0.09
     wrapped
    -0.09
    POSITIVE LOGITS
     watch
    0.11
     watching
    0.10
    ãģ¿
    0.10
    /list
    0.10
     closely
    0.10
     stare
    0.10
     gaze
    0.10
     Watching
    0.10
     observing
    0.10
     staring
    0.10
    Activations Density 0.001%

    No Known Activations