© 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. 34006
    Prev
    Next
    INDEX
    Explanations

    decrease in price or quantity

    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
    lek
    -0.10
    Ip
    -0.09
     Dim
    -0.09
     dein
    -0.09
    sky
    -0.08
    .si
    -0.08
    igi
    -0.08
     Huck
    -0.08
     unrealistic
    -0.08
    anche
    -0.08
    POSITIVE LOGITS
     slightly
    0.35
     slight
    0.26
     shave
    0.24
    ç¨į
    0.24
     increment
    0.22
     extra
    0.21
     shaved
    0.20
     margin
    0.20
     incremented
    0.20
     shaving
    0.20
    Activations Density 0.947%

    No Known Activations