© 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. 49677
    Prev
    Next
    INDEX
    Explanations

    gear VR, gear up, gear trains

    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
     Lotus
    -0.08
    uran
    -0.08
     Dexter
    -0.07
    LAS
    -0.07
    aston
    -0.07
     LAS
    -0.07
    eka
    -0.06
    ffc
    -0.06
     pretend
    -0.06
     Fe
    -0.06
    POSITIVE LOGITS
     gears
    0.19
     gear
    0.18
     Gear
    0.16
     gearing
    0.16
    shift
    0.16
    Gear
    0.16
     geared
    0.14
    boxes
    0.14
    ç®±
    0.14
    blend
    0.14
    Activations Density 0.025%

    No Known Activations