© 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. 87647
    Prev
    Next
    INDEX
    Explanations

    reflecting, absorbing, or conducting signals

    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
    ampo
    -0.09
    anus
    -0.09
     Swe
    -0.09
     lungs
    -0.09
     boarded
    -0.09
     Peace
    -0.09
     anus
    -0.09
    imore
    -0.09
     curtain
    -0.09
    olen
    -0.09
    POSITIVE LOGITS
     sunlight
    0.24
     incoming
    0.21
     photons
    0.21
     signals
    0.19
     bullets
    0.19
     messages
    0.18
     electricity
    0.17
     heat
    0.17
     nutrients
    0.17
     rays
    0.17
    Activations Density 1.389%

    No Known Activations