© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    android attributes: padding, margin, orientation

    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
     Riley
    -0.10
    oref
    -0.09
    illy
    -0.09
    azio
    -0.08
    rie
    -0.08
     hoof
    -0.08
    umo
    -0.08
     nada
    -0.08
     pans
    -0.08
     Cha
    -0.08
    POSITIVE LOGITS
    /-
    0.12
     Vanguard
    0.09
    anel
    0.09
     PRES
    0.09
     Inform
    0.09
     obligated
    0.09
     relatively
    0.09
    _lastname
    0.08
     inform
    0.08
    enegro
    0.08
    Activations Density 2.013%

    No Known Activations