© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8245
    Prev
    Next
    INDEX
    Explanations

    walking and standing 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
    Negative Logits
     Gat
    -0.11
     scare
    -0.10
    hic
    -0.10
     rac
    -0.10
     Kiss
    -0.09
     Govern
    -0.09
    annel
    -0.09
     fearful
    -0.09
    pow
    -0.09
    resher
    -0.09
    POSITIVE LOGITS
     standing
    0.28
     walking
    0.27
     Walking
    0.24
     Standing
    0.24
     feet
    0.23
    Walking
    0.23
    Standing
    0.22
     walkers
    0.20
     walked
    0.20
     foot
    0.20
    Activations Density 0.235%

    No Known Activations