© 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. 117501
    Prev
    Next
    INDEX
    Explanations

    offers, effect, points, tracks, snack

    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
    orde
    -0.10
    ern
    -0.10
    ivism
    -0.10
    side
    -0.10
    ures
    -0.10
    tone
    -0.10
    erness
    -0.10
    ness
    -0.10
    aal
    -0.10
    er
    -0.09
    POSITIVE LOGITS
    ycastle
    0.10
    strap
    0.10
    boom
    0.10
    cki
    0.09
    opsis
    0.09
    illo
    0.09
    amide
    0.08
    thon
    0.08
     dude
    0.08
     ipsum
    0.08
    Activations Density 0.003%

    No Known Activations