© 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. 112200
    Prev
    Next
    INDEX
    Explanations

    `after` 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
     yourself
    -0.10
     myself
    -0.09
     yourselves
    -0.09
     ourselves
    -0.08
     articulate
    -0.08
    :');↵
    -0.07
     ClassName
    -0.07
    bject
    -0.07
    isan
    -0.07
     Stam
    -0.07
    POSITIVE LOGITS
     after
    0.18
     while
    0.14
     AFTER
    0.13
     during
    0.13
     UPDATED
    0.13
     whilst
    0.12
    after
    0.12
     twice
    0.12
     après
    0.12
     despite
    0.11
    Activations Density 0.066%

    No Known Activations