© 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. 112712
    Prev
    Next
    INDEX
    Explanations

    calculation, computation, or calculator

    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
     Furious
    -0.10
    aja
    -0.09
    chk
    -0.09
    Liked
    -0.09
     Prelude
    -0.09
    otine
    -0.08
    .makeText
    -0.08
     Marketplace
    -0.08
     Plains
    -0.08
     latter
    -0.08
    POSITIVE LOGITS
    ematic
    0.10
    atively
    0.10
    oire
    0.10
    reuse
    0.09
    /count
    0.09
    /cal
    0.09
    enance
    0.09
    ULATOR
    0.09
    /math
    0.09
    ably
    0.08
    Activations Density 0.309%

    No Known Activations