© 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. 8209
    Prev
    Next
    INDEX
    Explanations

    transparent / transparency

    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
    ifs
    -0.11
    atts
    -0.09
    tings
    -0.09
    iness
    -0.09
    erm
    -0.09
    vol
    -0.09
     exp
    -0.09
    lev
    -0.09
    /pi
    -0.09
     slopes
    -0.09
    POSITIVE LOGITS
    /trans
    0.17
     Transparent
    0.15
    -transparent
    0.14
     transparency
    0.14
    Transparent
    0.14
     Transparency
    0.13
     transparent
    0.12
    transparent
    0.11
    /op
    0.11
    ly
    0.11
    Activations Density 0.040%

    No Known Activations