© 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. 114633
    Prev
    Next
    INDEX
    Explanations

    park and park features

    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
     rooms
    -0.14
     bedroom
    -0.14
     Bedrooms
    -0.14
     bedrooms
    -0.14
     Rooms
    -0.13
     room
    -0.13
     Room
    -0.13
     upstairs
    -0.13
     cellar
    -0.13
     showroom
    -0.13
    POSITIVE LOGITS
     park
    0.44
     parks
    0.35
     Parks
    0.30
    Park
    0.30
     Park
    0.29
    park
    0.28
     PARK
    0.25
     picnic
    0.23
     benches
    0.23
     bench
    0.22
    Activations Density 0.223%

    No Known Activations