© 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. 32167
    Prev
    Next
    INDEX
    Explanations

    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
    hoff
    -0.09
     coaster
    -0.09
     branding
    -0.09
     rode
    -0.09
     Bez
    -0.08
     Mou
    -0.08
     cords
    -0.08
    attr
    -0.08
     cuffs
    -0.08
    Beautiful
    -0.08
    POSITIVE LOGITS
     sitting
    0.20
     standing
    0.19
     Sitting
    0.17
     upright
    0.17
     seated
    0.17
     Standing
    0.16
     lying
    0.16
    -standing
    0.16
     sit
    0.15
     kneeling
    0.14
    Activations Density 0.059%

    No Known Activations