© 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. 7756
    Prev
    Next
    INDEX
    Explanations

    programming code or syntax

    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
     formulated
    -0.11
    -produced
    -0.11
     curated
    -0.11
     penned
    -0.11
     unde
    -0.10
     convo
    -0.10
     freshly
    -0.10
     newly
    -0.10
     compiled
    -0.10
     organised
    -0.10
    POSITIVE LOGITS
     anew
    0.13
     using
    0.13
    using
    0.13
    ä¾Ľ
    0.13
     based
    0.12
    based
    0.11
     incorporating
    0.11
    Fed
    0.10
     targeting
    0.10
     utilizing
    0.10
    Activations Density 2.564%

    No Known Activations