© 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. 28511
    Prev
    Next
    INDEX
    Explanations

    delay, pause, temporary

    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
     Reject
    -0.11
     Chow
    -0.11
     swiftly
    -0.11
    735
    -0.10
    adro
    -0.10
    -basic
    -0.10
     rejected
    -0.10
     capitals
    -0.10
     norm
    -0.10
    aku
    -0.10
    POSITIVE LOGITS
     merely
    0.20
     postpon
    0.19
     temporarily
    0.18
     pause
    0.17
     temporary
    0.17
     delay
    0.17
     postponed
    0.17
     slowdown
    0.16
     Pause
    0.16
     slowed
    0.16
    Activations Density 0.312%

    No Known Activations