© 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. 50710
    Prev
    Next
    INDEX
    Explanations

    energy, essence, or force

    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
    Not in Any Lists

    No Comments

    Negative Logits
     intim
    -0.12
     Borg
    -0.11
    unte
    -0.11
    лем
    -0.11
    zion
    -0.11
     inters
    -0.11
     Schiff
    -0.10
    vang
    -0.10
     INTERRU
    -0.10
     interpol
    -0.10
    POSITIVE LOGITS
     transferred
    0.18
     energy
    0.18
     flowing
    0.18
     flows
    0.17
     transfer
    0.16
     energies
    0.16
     flow
    0.15
     powers
    0.14
     eman
    0.14
     stored
    0.14
    Activations Density 0.165%

    No Known Activations