© 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. 4741
    Prev
    Next
    INDEX
    Explanations

    shelves and closets

    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
     fountain
    -0.16
     tables
    -0.14
     Fountain
    -0.13
     Restaurants
    -0.12
     pits
    -0.12
     underwater
    -0.12
     dock
    -0.12
    _tables
    -0.11
     crater
    -0.11
     gardens
    -0.11
    POSITIVE LOGITS
     shelves
    0.23
     shelf
    0.23
     closet
    0.21
     shel
    0.20
     Closet
    0.19
    shelf
    0.19
     clothes
    0.18
     Clothes
    0.17
     storage
    0.17
     Shelf
    0.17
    Activations Density 0.068%

    No Known Activations