© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47153
    Prev
    Next
    INDEX
    Explanations

    "About" or "Search"

    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
     foregoing
    -0.11
    semb
    -0.10
     <![
    -0.10
     Ling
    -0.10
     ech
    -0.10
     Raf
    -0.10
    INF
    -0.10
     bumped
    -0.10
    argout
    -0.10
     puff
    -0.10
    POSITIVE LOGITS
    irth
    0.09
     Prel
    0.09
     spr
    0.09
     mund
    0.08
    aken
    0.08
     Buckley
    0.08
     Spr
    0.07
    hek
    0.07
     Pron
    0.07
     Nunes
    0.07
    Activations Density 0.388%

    No Known Activations