© 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. 14120
    Prev
    Next
    INDEX
    Explanations

    consuming energy and resources

    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
    ando
    -0.11
    markup
    -0.11
     tucked
    -0.11
    erten
    -0.10
     Apprec
    -0.10
     onto
    -0.10
     defe
    -0.10
    Ware
    -0.10
     shoulders
    -0.10
    tract
    -0.10
    POSITIVE LOGITS
     calories
    0.12
     flames
    0.12
     Kad
    0.09
    çĦ
    0.09
     passion
    0.09
     utterly
    0.09
     entirety
    0.09
    cop
    0.09
     resources
    0.09
    ption
    0.08
    Activations Density 0.032%

    No Known Activations