© 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. 33984
    Prev
    Next
    INDEX
    Explanations

    long time periods

    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
     Edmund
    -0.09
    _fr
    -0.09
     sour
    -0.09
    lk
    -0.09
     nowhere
    -0.09
     rak
    -0.09
    ock
    -0.09
    cock
    -0.09
     midterm
    -0.09
    edly
    -0.09
    POSITIVE LOGITS
     endured
    0.10
     awaited
    0.10
     Sized
    0.10
     TT
    0.09
     harassed
    0.09
     when
    0.09
     ago
    0.09
    when
    0.09
     wait
    0.09
    fork
    0.09
    Activations Density 0.009%

    No Known Activations