© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7537
    Prev
    Next
    INDEX
    Explanations

    large numbers and quantities

    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
    aver
    -0.10
    adol
    -0.09
    cco
    -0.09
    ;;↵↵
    -0.09
     brav
    -0.08
    usch
    -0.08
     patron
    -0.08
    commons
    -0.08
     pro
    -0.08
    ORB
    -0.08
    POSITIVE LOGITS
     million
    0.24
     thousand
    0.23
     hundred
    0.20
     dozen
    0.19
     billion
    0.19
     lakh
    0.18
     Million
    0.16
    million
    0.15
     trillion
    0.15
     Thousands
    0.15
    Activations Density 0.260%

    No Known Activations