© 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. 8268
    Prev
    Next
    INDEX
    Explanations

    on demand

    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
    fork
    -0.10
     fork
    -0.10
    irm
    -0.09
     firstly
    -0.09
    kah
    -0.09
    iny
    -0.09
     Drill
    -0.08
    -static
    -0.08
     embr
    -0.08
    _initial
    -0.08
    POSITIVE LOGITS
     whenever
    0.31
     anytime
    0.27
     demand
    0.26
     Whenever
    0.23
     whim
    0.22
     instant
    0.21
     instantly
    0.21
     Demand
    0.21
     demanded
    0.21
    -demand
    0.21
    Activations Density 0.435%

    No Known Activations