© 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. 117577
    Prev
    Next
    INDEX
    Explanations

    visible, view, visibility

    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
     Southampton
    -0.10
     BAS
    -0.10
     Listings
    -0.09
    ilo
    -0.09
     Wick
    -0.09
     Florian
    -0.09
     Bailey
    -0.09
    vip
    -0.09
    emu
    -0.08
     lied
    -0.08
    POSITIVE LOGITS
     visible
    0.34
     foreground
    0.29
     Visible
    0.26
     frame
    0.25
     visibility
    0.24
     view
    0.24
    -visible
    0.22
    visible
    0.22
    Visible
    0.22
     Visibility
    0.22
    Activations Density 0.283%

    No Known Activations