© 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. 46142
    Prev
    Next
    INDEX
    Explanations

    suggestion or proposal

    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
     begging
    -0.09
     begged
    -0.09
     Pers
    -0.09
    antz
    -0.09
     conversations
    -0.09
    glm
    -0.09
     gasoline
    -0.09
     gig
    -0.09
     siendo
    -0.09
     partly
    -0.09
    POSITIVE LOGITS
     postpon
    0.11
     to
    0.09
     we
    0.09
     they
    0.09
     exchanging
    0.09
     idea
    0.09
     Idea
    0.09
    uste
    0.08
     using
    0.08
    idea
    0.08
    Activations Density 0.005%

    No Known Activations