© 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. 30869
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    INESS
    -0.11
     Emmy
    -0.09
     CM
    -0.09
    HING
    -0.08
     <↵
    -0.08
     sob
    -0.08
     antics
    -0.08
    -sex
    -0.08
     Plain
    -0.08
    inars
    -0.08
    POSITIVE LOGITS
     Alta
    0.09
     prolifer
    0.09
     Mars
    0.09
     stakes
    0.09
    ensa
    0.09
    jam
    0.08
    Dock
    0.08
    junction
    0.08
     globalization
    0.08
     failing
    0.08
    Activations Density 0.000%

    No Known Activations