© 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. 24931
    Prev
    Next
    INDEX
    Explanations

    synthesis, enzymes, antioxidants

    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
    }while
    -0.12
     futures
    -0.12
     Buccane
    -0.11
     Boundary
    -0.11
     Peel
    -0.11
     Outside
    -0.11
     Brain
    -0.11
    cee
    -0.10
    /team
    -0.10
    ureen
    -0.10
    POSITIVE LOGITS
     Orr
    0.08
     Herman
    0.08
    emma
    0.08
     Ned
    0.07
    TI
    0.07
    /head
    0.07
     tim
    0.07
     Mach
    0.07
     mighty
    0.07
     Gem
    0.07
    Activations Density 0.001%

    No Known Activations