© 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. 46302
    Prev
    Next
    INDEX
    Explanations

    background processes or context

    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
     internally
    -0.11
     BIN
    -0.10
     alo
    -0.10
    itti
    -0.10
     halfway
    -0.10
     itself
    -0.10
    idos
    -0.10
     Allen
    -0.10
    ube
    -0.10
    ze
    -0.10
    POSITIVE LOGITS
    /on
    0.12
    /background
    0.10
    /in
    0.09
    /sub
    0.09
    -most
    0.09
     discre
    0.08
     Seam
    0.08
    /back
    0.08
    unto
    0.08
    nj
    0.08
    Activations Density 0.014%

    No Known Activations