© 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. 30793
    Prev
    Next
    INDEX
    Explanations

    window and door openings

    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
     Kern
    -0.11
    nett
    -0.10
    ettle
    -0.10
     MX
    -0.10
     Mend
    -0.10
     FCC
    -0.10
     scour
    -0.10
    NJ
    -0.10
     fatt
    -0.10
     Vect
    -0.10
    POSITIVE LOGITS
     window
    0.51
     windows
    0.46
     door
    0.38
     Window
    0.38
    window
    0.38
     doors
    0.36
    -window
    0.35
    Window
    0.33
     WINDOW
    0.31
    _window
    0.30
    Activations Density 0.159%

    No Known Activations