© 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. 87671
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "with", "in", or "our"

    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
     Bravo
    -0.10
    apl
    -0.10
     pep
    -0.09
     caut
    -0.09
    inel
    -0.09
     Shall
    -0.09
     concatenate
    -0.09
     MCC
    -0.09
    shall
    -0.09
     promot
    -0.09
    POSITIVE LOGITS
     deeply
    0.10
     Mis
    0.09
    olian
    0.09
     Jain
    0.09
     obsess
    0.09
    uko
    0.09
     stew
    0.09
     agon
    0.08
     Reign
    0.08
     thoughtful
    0.08
    Activations Density 0.411%

    No Known Activations