© 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. 16603
    Prev
    Next
    INDEX
    Explanations

    patches, regions, areas

    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
     Legs
    -0.11
     legs
    -0.11
     draped
    -0.10
    ket
    -0.09
     ket
    -0.09
    legs
    -0.09
     Beautiful
    -0.09
     nos
    -0.09
     Nim
    -0.09
     Line
    -0.09
    POSITIVE LOGITS
     area
    0.25
     areas
    0.22
     patches
    0.20
    areas
    0.19
     patch
    0.19
    area
    0.19
    Area
    0.18
    Areas
    0.17
     Area
    0.17
    _area
    0.17
    Activations Density 0.120%

    No Known Activations