© 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. 6010
    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
     interception
    -0.13
     Rou
    -0.10
     rou
    -0.10
     kok
    -0.10
     Zig
    -0.10
    {lng
    -0.10
     intercepted
    -0.09
     sliced
    -0.09
     Stephan
    -0.09
    -ro
    -0.09
    POSITIVE LOGITS
     besides
    0.09
     Missing
    0.09
    âĿ
    0.09
     lon
    0.09
     Museum
    0.09
     missing
    0.09
    inz
    0.08
     freshness
    0.08
     compared
    0.08
    phem
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.