© 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. 3641
    Prev
    Next
    INDEX
    Explanations

    at the time

    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
    scr
    -0.12
    ноп
    -0.11
    -r
    -0.11
    eld
    -0.10
    ippo
    -0.10
    seau
    -0.10
    br
    -0.10
     Gib
    -0.10
    .toArray
    -0.10
    idos
    -0.09
    POSITIVE LOGITS
     later
    0.10
     this
    0.09
    /Core
    0.09
     moment
    0.08
    oci
    0.08
     Lazar
    0.08
     forte
    0.08
     betrayed
    0.07
     segue
    0.07
     churn
    0.07
    Activations Density 0.202%

    No Known Activations