© 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. 6945
    Prev
    Next
    INDEX
    Explanations

    then, but, then, after

    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
     prem
    -0.08
    airo
    -0.07
     obsess
    -0.07
    andel
    -0.07
    etz
    -0.07
    DMI
    -0.07
     inaugur
    -0.06
    berger
    -0.06
    ACA
    -0.06
    bie
    -0.06
    POSITIVE LOGITS
     quickly
    0.33
     Quickly
    0.28
     soon
    0.27
     then
    0.24
     gradually
    0.23
     rapidly
    0.21
    soon
    0.21
    then
    0.21
     swiftly
    0.21
     Soon
    0.21
    Activations Density 0.075%

    No Known Activations