© 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. 117453
    Prev
    Next
    INDEX
    Explanations

    capitalize on or jump on

    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
    /request
    -0.11
     discipline
    -0.09
    ForObject
    -0.09
     Alic
    -0.09
    wahl
    -0.09
     moot
    -0.09
     Moose
    -0.09
     contempl
    -0.09
    ukt
    -0.09
     mood
    -0.09
    POSITIVE LOGITS
     exploiting
    0.42
     exploitation
    0.41
     opportun
    0.41
     exploit
    0.38
     exploited
    0.36
     profit
    0.35
     explo
    0.35
     opport
    0.34
     capitalize
    0.33
     Opport
    0.32
    Activations Density 0.234%

    No Known Activations