© 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. 3551
    Prev
    Next
    INDEX
    Explanations

    DNA strand repair and damage

    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
     dissect
    -0.12
    iba
    -0.10
     capit
    -0.10
     manners
    -0.10
     flush
    -0.09
     Leo
    -0.09
    ASP
    -0.09
    egra
    -0.09
     recharge
    -0.09
     sens
    -0.09
    POSITIVE LOGITS
     DNA
    0.24
    DNA
    0.21
     dna
    0.20
     chromosomes
    0.20
     coding
    0.18
    dna
    0.17
     strands
    0.17
     code
    0.17
     chromosome
    0.16
     strand
    0.15
    Activations Density 0.927%

    No Known Activations