© 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. 29441
    Prev
    Next
    INDEX
    Explanations

    hand or finger movement

    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
     Cummings
    -0.11
     spaced
    -0.09
     scrambled
    -0.09
     Hayden
    -0.09
     Hills
    -0.09
     Sach
    -0.09
     ward
    -0.09
     swirl
    -0.09
     communion
    -0.09
     Honey
    -0.08
    POSITIVE LOGITS
     fingers
    0.23
     fingert
    0.22
     finger
    0.21
     hands
    0.20
     fingertips
    0.19
     thumb
    0.19
    æīĭ
    0.19
     hand
    0.18
     fing
    0.17
    finger
    0.17
    Activations Density 0.139%

    No Known Activations