© 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. 46983
    Prev
    Next
    INDEX
    Explanations

    home appliances and bathroom fixtures

    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
     Scaffold
    -0.12
     scaff
    -0.12
     Dagger
    -0.11
    Processed
    -0.11
     scaffold
    -0.11
     Lub
    -0.11
     Hoy
    -0.10
    dag
    -0.10
     backbone
    -0.10
     Umb
    -0.10
    POSITIVE LOGITS
     appliance
    0.27
     appliances
    0.26
     dishwasher
    0.23
     refrigerator
    0.23
     stove
    0.21
     Appliances
    0.21
     fridge
    0.20
     oven
    0.19
     kitchen
    0.18
     cabinet
    0.18
    Activations Density 0.580%

    No Known Activations