© 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. 87785
    Prev
    Next
    INDEX
    Explanations

    news agency photo credits

    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
     Nimbus
    -0.12
    adt
    -0.10
    letter
    -0.10
     unheard
    -0.10
    -original
    -0.10
     prer
    -0.10
     abstract
    -0.10
     agg
    -0.09
     Clock
    -0.09
    abstract
    -0.09
    POSITIVE LOGITS
     AP
    0.21
    (AP
    0.19
    AP
    0.18
    /AP
    0.16
    .AP
    0.15
    AAP
    0.13
     Reuters
    0.12
    FILE
    0.12
    Associated
    0.12
     ap
    0.12
    Activations Density 0.630%

    No Known Activations