© 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. 92332
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    .sources
    -0.10
    /render
    -0.10
    cid
    -0.09
     Snyder
    -0.09
    prof
    -0.09
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.09
    isan
    -0.09
     Moj
    -0.09
     Vocal
    -0.09
     Oxygen
    -0.09
    POSITIVE LOGITS
    ipo
    0.11
    rou
    0.09
     Kinder
    0.09
    ippo
    0.09
    æĪ
    0.08
     Almighty
    0.08
     Linden
    0.08
     recip
    0.08
    .ru
    0.08
     Transit
    0.08
    Activations Density 0.052%

    No Known Activations