© 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. 87877
    Prev
    Next
    INDEX
    Explanations

    discovery

    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
     Kun
    -0.09
     VOID
    -0.08
    ACA
    -0.08
     irreversible
    -0.08
    UNC
    -0.08
     Kant
    -0.08
     Schw
    -0.07
     Ras
    -0.07
     Gund
    -0.07
    hots
    -0.07
    POSITIVE LOGITS
     discovery
    0.23
    Discovery
    0.20
     discovering
    0.19
     Discover
    0.19
     Discovery
    0.18
     discover
    0.18
     discovers
    0.17
     discoveries
    0.17
    Discover
    0.16
     discovered
    0.16
    Activations Density 0.053%

    No Known Activations