© 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. 50796
    Prev
    Next
    INDEX
    Explanations

    programming constructs and possessives

    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
     obesity
    -0.12
     obese
    -0.11
     morphology
    -0.11
     Obesity
    -0.11
     masked
    -0.11
     Morph
    -0.10
     Neb
    -0.10
     chubby
    -0.10
     visuals
    -0.10
     overweight
    -0.10
    POSITIVE LOGITS
     polite
    0.09
     Pv
    0.08
    aida
    0.08
    uyo
    0.08
    _poll
    0.08
    .setOnItemClickListener
    0.08
     benign
    0.08
     Libert
    0.08
    ivre
    0.08
    ania
    0.08
    Activations Density 0.125%

    No Known Activations