© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87976
    Prev
    Next
    INDEX
    Explanations

    movements, graceful, effortless

    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
     rud
    -0.11
     Samar
    -0.10
     brav
    -0.10
     cheek
    -0.10
     courage
    -0.10
     luck
    -0.09
    stin
    -0.09
     trembling
    -0.09
    zer
    -0.09
     twee
    -0.09
    POSITIVE LOGITS
     movements
    0.16
     movement
    0.16
     graceful
    0.13
    movement
    0.12
     gracefully
    0.12
     fluid
    0.11
     dancer
    0.11
     effortless
    0.11
     Movement
    0.11
     Mov
    0.11
    Activations Density 0.007%

    No Known Activations