© 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. 25249
    Prev
    Next
    INDEX
    Explanations

    bridge or gap

    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
     Dallas
    -0.09
     sticker
    -0.09
    pty
    -0.09
    belt
    -0.09
     paw
    -0.09
     stripes
    -0.09
     bleed
    -0.09
     spiral
    -0.08
     wound
    -0.08
     tiger
    -0.08
    POSITIVE LOGITS
     bridge
    0.18
    Bridge
    0.18
     Bridge
    0.17
     gap
    0.16
     bridges
    0.15
    gap
    0.14
     gaps
    0.14
     Bridges
    0.14
    bridge
    0.14
    Gap
    0.13
    Activations Density 0.285%

    No Known Activations