© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33039
    Prev
    Next
    INDEX
    Explanations

    protein and peptide synthesis

    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
    Not in Any Lists

    No Comments

    Negative Logits
     germ
    -0.11
     lineage
    -0.10
     pregn
    -0.10
     superv
    -0.09
     primitives
    -0.09
    uum
    -0.09
     Olive
    -0.09
    _primitive
    -0.08
     vehicle
    -0.08
     kut
    -0.08
    POSITIVE LOGITS
     protein
    0.40
     Protein
    0.38
    protein
    0.33
     proteins
    0.32
     prote
    0.28
     Prote
    0.27
     amino
    0.27
     peptide
    0.25
     peptides
    0.24
    rotein
    0.20
    Activations Density 2.903%

    No Known Activations