© 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. 14711
    Prev
    Next
    INDEX
    Explanations

    hand and body positions

    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
     intricate
    -0.11
     Sabb
    -0.11
     swings
    -0.10
     Bosch
    -0.10
    403
    -0.10
     intric
    -0.10
     Legisl
    -0.10
    mans
    -0.10
    itung
    -0.10
     blooms
    -0.10
    POSITIVE LOGITS
     thumb
    0.12
     thumbs
    0.12
     Palm
    0.09
     parallel
    0.09
     palm
    0.09
     treating
    0.08
     enclosing
    0.08
     onboard
    0.08
     perpendicular
    0.08
     initially
    0.08
    Activations Density 0.077%

    No Known Activations