© 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. 90278
    Prev
    Next
    INDEX
    Explanations

    building architectural descriptions

    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
    azu
    -0.12
     Cav
    -0.11
     honda
    -0.11
     Cave
    -0.11
     hobby
    -0.10
     rew
    -0.10
    isex
    -0.10
     Hobby
    -0.10
     Nad
    -0.10
    dess
    -0.10
    POSITIVE LOGITS
     buildings
    0.39
     Buildings
    0.32
     building
    0.30
     architectural
    0.30
     architecture
    0.27
     Building
    0.26
     architect
    0.25
    /build
    0.23
     Architect
    0.23
    Building
    0.23
    Activations Density 0.654%

    No Known Activations