© 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. 29548
    Prev
    Next
    INDEX
    Explanations

    vertical position or height

    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
     Turnbull
    -0.10
     undisclosed
    -0.09
     corridor
    -0.09
    ds
    -0.09
     Hatch
    -0.09
     Curtain
    -0.09
     Lane
    -0.08
     discretionary
    -0.08
     blinds
    -0.08
     tagging
    -0.08
    POSITIVE LOGITS
     elevation
    0.34
     elevated
    0.28
     elev
    0.28
     elevate
    0.28
     height
    0.27
     Elevated
    0.25
     heights
    0.25
     Elev
    0.24
    -height
    0.22
     Height
    0.21
    Activations Density 0.187%

    No Known Activations