© 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. 92405
    Prev
    Next
    INDEX
    Explanations

    compliance with terms

    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
    atoi
    -0.08
    eting
    -0.08
     única
    -0.08
    angi
    -0.08
    {/*
    -0.08
    Jur
    -0.07
    930
    -0.07
     Piper
    -0.07
     Commod
    -0.07
    ëŀ
    -0.07
    POSITIVE LOGITS
     disqualified
    0.11
     aggressively
    0.10
     blat
    0.10
     irres
    0.10
     WC
    0.09
     Austral
    0.09
     unemployed
    0.09
     incomplete
    0.09
     wc
    0.09
     Tat
    0.09
    Activations Density 0.005%

    No Known Activations