© 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. 92557
    Prev
    Next
    INDEX
    Explanations

    concepts and structures

    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
     themselves
    -0.14
     Gerald
    -0.10
     Yo
    -0.09
    zes
    -0.09
     griev
    -0.09
    Yo
    -0.09
     Mey
    -0.09
    AccessToken
    -0.09
    iken
    -0.08
     staged
    -0.08
    POSITIVE LOGITS
     itself
    0.12
    ’
    0.11
    мÑı
    0.10
    ray
    0.10
    SJ
    0.10
    stuff
    0.09
    izo
    0.09
    åŀĭ
    0.09
    DDS
    0.09
    imon
    0.08
    Activations Density 0.641%

    No Known Activations