© 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. 18708
    Prev
    Next
    INDEX
    Explanations

    place, hand, mind, air

    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
    xo
    -0.10
    980
    -0.09
     overlays
    -0.09
    fully
    -0.09
     Overlay
    -0.09
    iks
    -0.09
     overlay
    -0.09
    Overlay
    -0.08
     SEE
    -0.08
     Rub
    -0.08
    POSITIVE LOGITS
    /on
    0.13
    /generated
    0.11
    leck
    0.11
     Cann
    0.11
     Sal
    0.10
    Sal
    0.10
     Holl
    0.10
     circulation
    0.09
    eded
    0.09
    abouts
    0.09
    Activations Density 0.119%

    No Known Activations