© 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. 47201
    Prev
    Next
    INDEX
    Explanations

    place or structure

    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
     holes
    -0.11
     parenthesis
    -0.10
    -pocket
    -0.10
     tents
    -0.10
     vase
    -0.10
     trenches
    -0.10
     hole
    -0.10
     folder
    -0.10
     parentheses
    -0.10
    -off
    -0.10
    POSITIVE LOGITS
     couch
    0.19
     doorstep
    0.18
     shelf
    0.17
     ledge
    0.16
     platform
    0.15
     shelves
    0.15
     porch
    0.15
     bench
    0.14
     balcony
    0.14
     sofa
    0.14
    Activations Density 0.302%

    No Known Activations