© 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. 7755
    Prev
    Next
    INDEX
    Explanations

    while or during events

    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
    gee
    -0.11
    uat
    -0.10
    urs
    -0.10
    pen
    -0.10
    ubber
    -0.10
     Gle
    -0.09
     reluctantly
    -0.09
    ningen
    -0.09
    anta
    -0.09
    ning
    -0.09
    POSITIVE LOGITS
     while
    0.28
     WHILE
    0.24
     unexpectedly
    0.23
    while
    0.22
     whilst
    0.22
     during
    0.21
    	while
    0.19
    during
    0.17
    _while
    0.17
     While
    0.17
    Activations Density 0.412%

    No Known Activations