© 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. 87616
    Prev
    Next
    INDEX
    Explanations

    wrinkles or folds

    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
     comb
    -0.10
    (Cl
    -0.10
     ley
    -0.10
    pcb
    -0.09
     verd
    -0.09
     bleeding
    -0.09
     Beth
    -0.09
    èį
    -0.09
    (Editor
    -0.09
     Ops
    -0.09
    POSITIVE LOGITS
     wrinkles
    0.18
     folds
    0.17
     wrink
    0.17
     folding
    0.15
     fold
    0.14
     skin
    0.14
     Folding
    0.14
     folded
    0.13
     Skin
    0.12
     contracting
    0.12
    Activations Density 0.079%

    No Known Activations