© 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. 47875
    Prev
    Next
    INDEX
    Explanations

    before certain events or actions

    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
     preceded
    -0.13
     prepar
    -0.13
     interim
    -0.13
     anticipation
    -0.12
     preparations
    -0.12
     Earlier
    -0.12
     temporarily
    -0.12
     concurrently
    -0.12
     preparation
    -0.12
    yan
    -0.11
    POSITIVE LOGITS
     before
    0.38
    before
    0.31
     Before
    0.25
    Before
    0.25
     BEFORE
    0.24
     antes
    0.20
    _before
    0.20
    	before
    0.20
    -before
    0.20
     bevor
    0.18
    Activations Density 0.290%

    No Known Activations