© 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. 117439
    Prev
    Next
    INDEX
    Explanations

    its contents

    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
     desks
    -0.09
     Scheme
    -0.09
     residences
    -0.09
     buried
    -0.09
     pull
    -0.08
     simplest
    -0.08
     triumph
    -0.08
     warm
    -0.08
     Merry
    -0.08
     anv
    -0.08
    POSITIVE LOGITS
     Dort
    0.10
     traveler
    0.10
    Unavailable
    0.10
    ayo
    0.10
    esome
    0.10
    arb
    0.10
     voyage
    0.10
     Kaiser
    0.09
     Maar
    0.09
     Hat
    0.09
    Activations Density 0.024%

    No Known Activations