© 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. 14149
    Prev
    Next
    INDEX
    Explanations

    was first

    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
     Later
    -0.08
     Quickly
    -0.08
     tand
    -0.08
     Martins
    -0.08
    yle
    -0.08
     pretended
    -0.07
    parentNode
    -0.07
     TODAY
    -0.07
     aujourd
    -0.07
    Later
    -0.07
    POSITIVE LOGITS
     first
    0.42
     originally
    0.37
     started
    0.34
     initially
    0.34
    first
    0.33
     originated
    0.31
     began
    0.31
     Started
    0.29
     debuted
    0.29
    started
    0.28
    Activations Density 0.953%

    No Known Activations