© 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. 26724
    Prev
    Next
    INDEX
    Explanations

    wheelchair and related mobility devices

    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
     hike
    -0.11
     Stap
    -0.10
     implant
    -0.10
     stap
    -0.10
     ladder
    -0.10
     fel
    -0.09
     helicopt
    -0.09
    vik
    -0.09
     tec
    -0.09
    hap
    -0.09
    POSITIVE LOGITS
     wheels
    0.41
     wheel
    0.36
     whe
    0.36
     Wheels
    0.35
     Wheel
    0.31
    wheel
    0.31
    Wheel
    0.31
    -wheel
    0.29
     Whe
    0.28
     carts
    0.25
    Activations Density 0.278%

    No Known Activations