© 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. 29677
    Prev
    Next
    INDEX
    Explanations

    attire and body covering

    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
    Not in Any Lists

    No Comments

    Negative Logits
     launder
    -0.11
     washing
    -0.10
     laundering
    -0.10
     handic
    -0.10
    unpack
    -0.09
     unknow
    -0.09
     inadvert
    -0.09
    еж
    -0.09
     calm
    -0.09
     asleep
    -0.09
    POSITIVE LOGITS
     coverage
    0.13
    bare
    0.13
     strategically
    0.12
     unstable
    0.11
     functional
    0.11
     BDSM
    0.11
     covering
    0.11
     minimal
    0.11
    coverage
    0.10
     scant
    0.10
    Activations Density 0.015%

    No Known Activations