© 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. 3721
    Prev
    Next
    INDEX
    Explanations

    self-made, independent, or DIY projects

    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
    inous
    -0.09
     dead
    -0.08
     loung
    -0.07
    ials
    -0.07
    morph
    -0.07
     DEAD
    -0.07
     Koh
    -0.07
    öh
    -0.07
    headed
    -0.07
    rics
    -0.07
    POSITIVE LOGITS
     thresh
    0.11
    kers
    0.11
    .mx
    0.11
    /errors
    0.10
    ASP
    0.10
    ishly
    0.10
    -original
    0.10
    ipa
    0.10
    -work
    0.10
    ,__
    0.10
    Activations Density 0.054%

    No Known Activations