© 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. 18481
    Prev
    Next
    INDEX
    Explanations

    packing and moving services

    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
     nightly
    -0.11
     bedside
    -0.11
     Candle
    -0.11
     barber
    -0.10
     sitting
    -0.10
     Barber
    -0.10
     fluoride
    -0.10
     Dial
    -0.10
     bathing
    -0.10
    /Form
    -0.10
    POSITIVE LOGITS
     unpack
    0.32
     cargo
    0.27
    unpack
    0.25
     hauling
    0.25
     loading
    0.24
     packing
    0.24
     unload
    0.23
     luggage
    0.23
     Cargo
    0.23
     Packing
    0.23
    Activations Density 0.163%

    No Known Activations