© 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. 25171
    Prev
    Next
    INDEX
    Explanations

    wasted, loss, waste, wasteful

    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
     Sé
    -0.11
     triang
    -0.11
     unclear
    -0.10
    -now
    -0.09
    langs
    -0.09
     plung
    -0.09
     Steering
    -0.09
     cambi
    -0.09
     humili
    -0.09
    anse
    -0.09
    POSITIVE LOGITS
     wasted
    0.50
     wast
    0.45
     waste
    0.44
     wasting
    0.41
     Waste
    0.37
     wastes
    0.36
     unused
    0.34
     Unused
    0.27
    Unused
    0.25
    unused
    0.24
    Activations Density 0.396%

    No Known Activations