© 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. 13933
    Prev
    Next
    INDEX
    Explanations

    opening and closing

    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
     openings
    -0.20
     opening
    -0.16
     opens
    -0.15
     opened
    -0.15
     openness
    -0.15
    -opening
    -0.13
    å¼Ģ
    -0.12
    opening
    -0.12
    opened
    -0.11
     Opening
    -0.11
    POSITIVE LOGITS
    /close
    0.12
    .setRequestHeader
    0.11
    ulos
    0.11
    ndef
    0.10
     revealing
    0.10
     Inside
    0.10
    -close
    0.10
    IKE
    0.10
    \\\
    0.10
     onClose
    0.10
    Activations Density 0.283%

    No Known Activations