© 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. 88595
    Prev
    Next
    INDEX
    Explanations

    outdoor spaces like decks and terraces

    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
     saturation
    -0.11
     hurd
    -0.11
     Peggy
    -0.11
     Jeb
    -0.11
     stockings
    -0.10
     tö
    -0.10
     gallon
    -0.10
    midi
    -0.10
    åľ
    -0.10
     Tooltip
    -0.10
    POSITIVE LOGITS
     balcony
    0.34
     porch
    0.32
     terrace
    0.31
     patio
    0.31
     balcon
    0.30
     rooftop
    0.28
     deck
    0.26
     Deck
    0.24
     decks
    0.24
     outdoor
    0.22
    Activations Density 0.198%

    No Known Activations