© 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. 46042
    Prev
    Next
    INDEX
    Explanations

    English and language codes

    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
    cess
    -0.09
    ilee
    -0.09
     Nacht
    -0.09
     recurring
    -0.09
    Wake
    -0.09
     Thor
    -0.09
    eki
    -0.09
     Rare
    -0.09
    lla
    -0.09
     Tol
    -0.09
    POSITIVE LOGITS
     English
    0.16
     english
    0.11
    English
    0.11
     admir
    0.10
     Engl
    0.10
    eme
    0.10
    èĭ±
    0.09
     Garr
    0.09
     AIM
    0.09
    adt
    0.09
    Activations Density 0.070%

    No Known Activations