© 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. 49905
    Prev
    Next
    INDEX
    Explanations

    outdoor property 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
    onis
    -0.09
     cameras
    -0.09
     Beach
    -0.09
     vehicles
    -0.09
     vehicle
    -0.09
    ef
    -0.09
     Cameras
    -0.09
     buildings
    -0.09
     camera
    -0.09
     Wag
    -0.08
    POSITIVE LOGITS
     yard
    0.20
     driveway
    0.19
     lawn
    0.18
     front
    0.17
     backyard
    0.17
    -yard
    0.15
     Yard
    0.14
     yards
    0.13
     porch
    0.13
     courtyard
    0.12
    Activations Density 0.073%

    No Known Activations