© 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. 18669
    Prev
    Next
    INDEX
    Explanations

    happy to schedule

    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
     Gors
    -0.12
    elon
    -0.12
     lifted
    -0.10
     amplified
    -0.10
    vig
    -0.10
     eg
    -0.10
    ouse
    -0.10
     aspiring
    -0.10
     Herb
    -0.09
    ela
    -0.09
    POSITIVE LOGITS
     welcoming
    0.10
    hap
    0.09
     Kore
    0.09
     sew
    0.09
     welcomed
    0.09
     hay
    0.08
     welcome
    0.08
     consulted
    0.08
    kip
    0.08
     conc
    0.08
    Activations Density 0.001%

    No Known Activations