© 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. 28513
    Prev
    Next
    INDEX
    Explanations

    load of, load time, load sharing, load shedding

    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
    rete
    -0.12
    uted
    -0.11
    ute
    -0.11
    dish
    -0.11
    -suite
    -0.11
    ante
    -0.10
     severed
    -0.10
    ged
    -0.10
    fen
    -0.10
    tons
    -0.10
    POSITIVE LOGITS
    peaker
    0.09
     consolidated
    0.08
    breaking
    0.08
    ings
    0.08
    speaker
    0.08
    -bearing
    0.08
    aes
    0.08
    ças
    0.08
    SOR
    0.08
    out
    0.07
    Activations Density 0.027%

    No Known Activations