© 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. 14168
    Prev
    Next
    INDEX
    Explanations

    returns and refunds

    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
    Not in Any Lists

    No Comments

    Negative Logits
     perpetr
    -0.13
     Coc
    -0.12
     thirst
    -0.11
    uzzi
    -0.11
    oose
    -0.11
    gan
    -0.11
     depleted
    -0.11
    aget
    -0.10
    gre
    -0.10
    normalized
    -0.10
    POSITIVE LOGITS
     refund
    0.33
     refunds
    0.28
     return
    0.28
     returns
    0.28
     warranty
    0.27
     refunded
    0.25
     Return
    0.23
     Warranty
    0.23
     Returns
    0.23
    -return
    0.22
    Activations Density 0.145%

    No Known Activations