© 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. 114316
    Prev
    Next
    INDEX
    Explanations

    round

    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
    iest
    -0.12
    esis
    -0.12
    ktor
    -0.10
     Torch
    -0.09
     realization
    -0.09
    rex
    -0.09
    reira
    -0.09
    erm
    -0.09
     Outreach
    -0.09
    edu
    -0.09
    POSITIVE LOGITS
     Round
    0.20
     round
    0.20
    -round
    0.19
     robin
    0.18
     rounds
    0.18
    round
    0.17
    Round
    0.17
     rounded
    0.17
     Rounds
    0.16
    (round
    0.16
    Activations Density 0.045%

    No Known Activations