© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16454
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations

    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
     Shea
    -0.10
     fond
    -0.08
     ARGS
    -0.08
     Stall
    -0.08
    BW
    -0.08
    {},
    -0.07
     Dust
    -0.07
    470
    -0.07
     Sv
    -0.07
    atur
    -0.07
    POSITIVE LOGITS
     sum
    0.29
     plus
    0.26
     sums
    0.24
     multiplication
    0.24
     Sum
    0.23
     multiplied
    0.22
    Sum
    0.22
     suma
    0.21
     arithmetic
    0.21
     equals
    0.21
    Activations Density 0.595%

    No Known Activations