© 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. 112725
    Prev
    Next
    INDEX
    Explanations

    can help

    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
     anytime
    -0.09
     cela
    -0.09
     sometimes
    -0.08
     such
    -0.08
     fool
    -0.08
     luck
    -0.08
    Mono
    -0.08
     Skyl
    -0.07
     Luck
    -0.07
     ones
    -0.07
    POSITIVE LOGITS
    chw
    0.10
     Gree
    0.10
     strives
    0.10
     agre
    0.10
     probably
    0.10
     faithfully
    0.10
     gladly
    0.10
     obl
    0.10
    .gca
    0.10
     Probably
    0.09
    Activations Density 0.029%

    No Known Activations