© 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. 90714
    Prev
    Next
    INDEX
    Explanations

    when movements happen

    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
    adge
    -0.11
     afterwards
    -0.11
    spath
    -0.10
    unday
    -0.10
    brightness
    -0.10
    spir
    -0.10
     Maison
    -0.10
     urgently
    -0.10
    lan
    -0.09
    lad
    -0.09
    POSITIVE LOGITS
     whenever
    0.28
     everytime
    0.23
     Whenever
    0.22
    Whenever
    0.22
     walking
    0.21
     when
    0.18
     movements
    0.18
     movement
    0.17
    when
    0.17
     Walking
    0.16
    Activations Density 0.581%

    No Known Activations