© 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. 87707
    Prev
    Next
    INDEX
    Explanations

    temporary duration

    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
     awaited
    -0.10
     confidently
    -0.10
     await
    -0.10
    ardi
    -0.10
     myster
    -0.10
    aub
    -0.10
     somehow
    -0.10
     wait
    -0.10
    anst
    -0.10
     eagerly
    -0.10
    POSITIVE LOGITS
     momentarily
    0.13
     temporarily
    0.11
     briefly
    0.10
     ONLY
    0.10
     recomm
    0.09
     Asked
    0.09
     presently
    0.09
     gentle
    0.09
     shortly
    0.09
    onna
    0.09
    Activations Density 0.038%

    No Known Activations