© 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. 88398
    Prev
    Next
    INDEX
    Explanations

    Swan Hill, Ivory Coast, phant shark

    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
     Piper
    -0.10
    elters
    -0.10
     unb
    -0.09
    ôme
    -0.09
     mang
    -0.08
     peppers
    -0.08
    rase
    -0.08
     Bauer
    -0.08
     squirrel
    -0.08
    ulo
    -0.08
    POSITIVE LOGITS
    ensch
    0.11
    ston
    0.11
    /at
    0.10
     tus
    0.10
    cea
    0.09
    abal
    0.09
    569
    0.09
    endon
    0.09
    -white
    0.09
    iste
    0.09
    Activations Density 0.039%

    No Known Activations