© 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. 87648
    Prev
    Next
    INDEX
    Explanations

    hope that it will be useful

    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
     Brewer
    -0.10
    egrator
    -0.10
    gm
    -0.10
    ano
    -0.10
    continent
    -0.10
     pars
    -0.09
     :-↵
    -0.09
    eric
    -0.09
    -final
    -0.09
    (if
    -0.09
    POSITIVE LOGITS
     Derrick
    0.10
     subsection
    0.10
     Penny
    0.09
    bach
    0.09
    ACL
    0.09
    нÑı
    0.08
    -foot
    0.08
     seasonal
    0.08
     overl
    0.08
     halfway
    0.08
    Activations Density 0.001%

    No Known Activations