© 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. 48359
    Prev
    Next
    INDEX
    Explanations

    body position and movement of limbs

    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
    neau
    -0.10
    opor
    -0.10
    æ²»
    -0.10
     Imported
    -0.10
     blanket
    -0.09
     cape
    -0.09
     pij
    -0.09
    imity
    -0.09
    -hooks
    -0.09
    avec
    -0.09
    POSITIVE LOGITS
     straight
    0.11
     flex
    0.11
     strained
    0.11
     stead
    0.10
     angle
    0.10
     pushing
    0.10
     stretch
    0.09
     powering
    0.09
    extension
    0.09
     push
    0.09
    Activations Density 0.068%

    No Known Activations