© 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. 14249
    Prev
    Next
    INDEX
    Explanations

    keep in mind

    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
    pedia
    -0.11
    adge
    -0.11
     out
    -0.10
    inki
    -0.10
     herein
    -0.10
    dense
    -0.10
     away
    -0.10
    ty
    -0.09
    ?,↵
    -0.09
     Apart
    -0.09
    POSITIVE LOGITS
    elas
    0.09
    ame
    0.09
     that
    0.09
     how
    0.08
    /on
    0.07
     Scotch
    0.07
    tridge
    0.07
    ario
    0.07
    957
    0.07
     whether
    0.07
    Activations Density 0.010%

    No Known Activations