© 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. 15997
    Prev
    Next
    INDEX
    Explanations

    following movements or tracking

    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
    WL
    -0.10
     Britann
    -0.09
    RES
    -0.09
     repeatedly
    -0.09
    Beh
    -0.09
     appropriate
    -0.09
     Wheeler
    -0.09
     Beh
    -0.09
    ubb
    -0.09
     toughness
    -0.09
    POSITIVE LOGITS
     Tracking
    0.15
     tracking
    0.15
     movements
    0.13
     tracked
    0.13
     movement
    0.13
    -tracking
    0.12
    tracking
    0.12
     travels
    0.11
    Tracker
    0.11
     trackers
    0.11
    Activations Density 0.052%

    No Known Activations