© 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. 49824
    Prev
    Next
    INDEX
    Explanations

    raising hands or holding objects

    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
     dood
    -0.10
     ambient
    -0.10
    anno
    -0.10
     ruth
    -0.10
     discontinued
    -0.10
     shed
    -0.10
    olu
    -0.09
    efficient
    -0.09
    unft
    -0.09
     Valve
    -0.09
    POSITIVE LOGITS
     arms
    0.22
     palms
    0.19
    arms
    0.17
     palm
    0.16
     Arms
    0.16
     gesture
    0.15
     hands
    0.14
     open
    0.14
     gestures
    0.13
     raised
    0.13
    Activations Density 0.052%

    No Known Activations