© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27574
    Prev
    Next
    INDEX
    Explanations

    URLs in text

    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
    eken
    -0.10
     whoever
    -0.10
    :http
    -0.09
     ups
    -0.09
     eater
    -0.09
     Archived
    -0.09
     announcements
    -0.09
     POLIT
    -0.08
     Cocktail
    -0.08
     overs
    -0.08
    POSITIVE LOGITS
     hood
    0.09
    .World
    0.09
     meilleure
    0.08
     Contemporary
    0.08
    ï¼Īç¬ij
    0.08
    omain
    0.08
    ULT
    0.08
     Fundamental
    0.08
    .sh
    0.08
     laten
    0.08
    Activations Density 0.092%

    No Known Activations