© 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. 89864
    Prev
    Next
    INDEX
    Explanations

    gestures, poses, and exercises

    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
    Dispatch
    -0.09
     retal
    -0.09
    ici
    -0.09
     Laden
    -0.09
     Heights
    -0.09
     ord
    -0.09
     cracked
    -0.09
    418
    -0.09
     lined
    -0.09
     Slate
    -0.09
    POSITIVE LOGITS
     salute
    0.22
     pose
    0.16
     handshake
    0.15
     gesture
    0.15
     poses
    0.15
     knot
    0.14
     gestures
    0.14
     yoga
    0.13
     thumbs
    0.13
     maneuvers
    0.13
    Activations Density 0.181%

    No Known Activations