© 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. 25229
    Prev
    Next
    INDEX
    Explanations

    names starting with Mont, Marc, Mor, Ar, Sil, Ved, Gust

    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
     Nagar
    -0.08
    pt
    -0.08
     pe
    -0.08
     tor
    -0.07
     Sab
    -0.07
     Manuel
    -0.07
     Pty
    -0.07
    man
    -0.07
    ing
    -0.07
    ifier
    -0.07
    POSITIVE LOGITS
    _Metadata
    0.10
    istique
    0.10
    -bs
    0.10
    /settings
    0.09
    (KP
    0.09
     Ont
    0.09
    _Collections
    0.09
    contro
    0.09
    iqué
    0.09
    eea
    0.09
    Activations Density 0.773%

    No Known Activations