© 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. 8132
    Prev
    Next
    INDEX
    Explanations

    locations above or on floors

    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
     below
    -0.12
     underneath
    -0.10
     beneath
    -0.10
     ground
    -0.10
    IPP
    -0.09
    aket
    -0.09
    Below
    -0.09
     Below
    -0.09
     deeply
    -0.08
     deepest
    -0.08
    POSITIVE LOGITS
     above
    0.31
     Above
    0.29
     overhead
    0.28
    above
    0.28
    Above
    0.27
     ABOVE
    0.25
     overlooking
    0.24
     atop
    0.22
     alo
    0.21
    _above
    0.21
    Activations Density 0.261%

    No Known Activations